© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3661
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming examples

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.86
    antaranya
    -0.75
    PhysRevD
    -0.74
     onAnimation
    -0.71
    extAlignment
    -0.70
    bootstrapcdn
    -0.66
    principalColumn
    -0.65
    CppCodeGen
    -0.61
    labelledby
    -0.60
    hObject
    -0.58
    POSITIVE LOGITS
    ```
    0.70
     ```
    0.68
    +```
    0.66
    __(/*!
    0.64
    EndContext
    0.58
     الحره
    0.57
    <tbody>
    0.54
     estimés
    0.54
     سكانية
    0.52
     виправивши
    0.52
    Activations Density 0.081%

    No Known Activations