© 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. 1-CLT-HP
    7. 10173
    Prev
    Next
    INDEX
    Explanations

    ocyto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocyto
    -0.76
    .*")]
    -0.68
    }{*}{}
    -0.58
    gettyimages
    -0.55
     Avery
    -0.54
    parsedMessage
    -0.54
    waltung
    -0.54
     bezeichneter
    -0.53
     Audiodateien
    -0.52
    %";
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.63
    Jeografia
    0.59
    PreExecute
    0.59
    UnitTesting
    0.58
    Brainz
    0.51
    matis
    0.50
    すす
    0.49
    EqualsAnd
    0.47
    QtWidgets
    0.47
    StreetMap
    0.47
    Activations Density 0.294%

    No Known Activations