© 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. 9186
    Prev
    Next
    INDEX
    Explanations

    province

    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
    set
    -0.52
    sets
    -0.46
     roofs
    -0.46
     roof
    -0.45
    ์
    -0.43
     ROOF
    -0.42
    Roof
    -0.42
     Roof
    -0.40
    qk
    -0.40
    SourceChecksum
    -0.40
    POSITIVE LOGITS
    findpost
    0.80
    parsedMessage
    0.77
    oughby
    0.69
     habido
    0.68
    eseorang
    0.65
    __*/
    0.65
    ötzlich
    0.64
    جغرافيا
    0.63
    ergies
    0.63
    tiary
    0.63
    Activations Density 0.019%

    No Known Activations