© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 800
    Prev
    Next
    INDEX
    Explanations

    block comments and public static declarations in code

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    aarrggbb
    -0.58
    mism
    -0.57
    if
    -0.52
    եռ
    -0.51
    ::$_
    -0.47
    writeFieldEnd
    -0.47
     typelib
    -0.47
    AddHtmlAttribute
    -0.46
    cings
    -0.46
    avons
    -0.45
    POSITIVE LOGITS
    public
    2.22
     public
    1.98
    private
    1.41
    protected
    1.32
     private
    1.24
     PUBLIC
    1.22
     Public
    1.19
    PUBLIC
    1.12
    Public
    1.09
     protected
    1.00
    Activations Density 0.537%

    No Known Activations