© 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. 3-RES-MATRYOSHKA-DC
    7. 2898
    Prev
    Next
    INDEX
    Explanations

    asterisks for emphasis

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unhofer
    -0.74
    xnn
    -0.67
    __(/*!
    -0.66
     Waray
    -0.64
    WriteBarrier
    -0.62
     Dory
    -0.62
     Lorna
    -0.60
    󠁢
    -0.60
    ContentAlignment
    -0.60
    abetes
    -0.59
    POSITIVE LOGITS
    *\
    1.91
     *\
    0.73
    @",
    0.60
    ValueOf
    0.58
    ächt
    0.56
    pushFollow
    0.56
    litos
    0.56
    WebServlet
    0.56
    makeConstraints
    0.55
    Hust
    0.54
    Activations Density 0.010%

    No Known Activations