---
description: "Co-occurrence and the matrix: reading the heatmap, spotting clusters and bridges, the high-similarity warning, and filtering the noise down."
---
<!--
  Markdown representation of https://docs.jotaid.com/en/guide/matrix
  Generated by scripts/gen-markdown-variants.mjs — do not edit by hand.
  Served from the canonical URL under `Accept: text/markdown`.
-->

# Co-occurrence & Matrix

**Co-occurrence** is a plain fact: two nodes appearing in **the same note**. The moment you write `[[A]]` and `[[B]]` together, they have co-occurred once.

The graph draws that as a line; the matrix lays it out as a grid — **one dataset, two readings**.

## Connection Strength

A cell's depth is the **strength** of the relationship: how much of the time two concepts turn up together.

- Two concepts that always appear together → a deep cell
- Each appearing often, together rarely → a pale cell

The important part is that it measures **what proportion of the time**, not how many times. A pair appearing 100 times each and 5 times together comes out weak — those 5 were probably incidental. That is what makes cells comparable: a deep cell in a busy corner of your notes means the same thing as a deep cell anywhere else.

The colour language holds across the app: **deeper blue = stronger**, so moving between the matrix and the [graph](https://docs.jotaid.com/en/guide/graph) needs no relearning.

## Reading the Structure

| What you see | What it means |
|--------------|---------------|
| **Bright blocks on the diagonal** | A cluster — these concepts all relate strongly; brackets mark its bounds |
| **Bright cells between blocks** | A bridge — a relationship joining two otherwise separate clusters |
| **Largely empty rows/columns** | Isolated nodes, barely co-occurring with anything |

Open a cell and the panel says whether the pair sits in the **same cluster** or **different clusters**. Strong cross-cluster relationships are often the most interesting — they join two lines of thought.

## The High-Similarity Warning

The very strongest cells are flagged **High Similarity** in the warning colour. Overlap that heavy usually means one thing:

> These may be **two names for the same concept**.

"User retention" and "retention rate", say. The right move there is usually not to link them but to [merge the nodes](https://docs.jotaid.com/en/guide/manage-nodes).

## Filtering the Noise Down

With many nodes the matrix turns to mush. The filter panel offers three dials:

| Filter | Use |
|--------|-----|
| **Minimum co-occurrences** | Pairs that co-occurred once are mostly incidental; 2 or 3 clears things up |
| **Strength range** | Raise the floor for strong relationships only, or lower the ceiling to hunt weak ones |
| **By badge** | Restrict to Core / Bridge / Emerging |

## Using It

1. Go to **Node view** and switch to **Matrix** (on iOS, the segmented capsule at the bottom toggles Graph / Matrix)
2. **Hover** (macOS) or **tap** (iOS) a cell for that pair's details
3. The panel also lists each node's **strongest partners**, so you can keep following the thread

> **When the matrix starts paying off**
>
> Patterns begin to surface at around 10 notes with backlinks — the more links, the clearer the structure. With [Pro](https://docs.jotaid.com/en/guide/pricing) and a key, you can also have [the AI explain](https://docs.jotaid.com/en/guide/ai-suggestions) what is behind a bright cell.

## It Sees the Current Project Only

The matrix, the [graph](https://docs.jotaid.com/en/guide/graph) and the network summary all cover the **currently selected project**.

## Next Steps

- [Link Predictions](https://docs.jotaid.com/en/guide/predictions) — Pairs that never co-occurred but might belong together
- [Knowledge Graph](https://docs.jotaid.com/en/guide/graph) — The same data as a network
- [AI Interpretation](https://docs.jotaid.com/en/guide/ai-suggestions) — Having the AI explain a strong relationship