© 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. 4-CLT-HP
    7. 1806
    Prev
    Next
    INDEX
    Explanations

    order

    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
     ""],
    -0.54
     astore
    -0.51
     penalty
    -0.51
    templateUrl
    -0.50
    cookieParser
    -0.50
    ristan
    -0.49
    lexikon
    -0.47
     householder
    -0.47
     Gedicht
    -0.46
     comparaison
    -0.46
    POSITIVE LOGITS
     estekak
    0.75
     مرئيه
    0.62
    IntoConstraints
    0.57
    vallis
    0.54
    RenderAtEndOf
    0.54
    +#+#
    0.53
    windowFixed
    0.53
     arşivlendi
    0.53
    sproz
    0.52
     déterminé
    0.52
    Activations Density 0.003%

    No Known Activations