© 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. 9821
    Prev
    Next
    INDEX
    Explanations

    of

    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
    MigrationBuilder
    -0.62
    __);
    -0.60
    ​—
    -0.59
    Writ
    -0.59
    HasColumnName
    -0.59
    例文帳に追加
    -0.58
    TypedDataSet
    -0.57
     amorti
    -0.57
    windowFixed
    -0.57
    databinding
    -0.56
    POSITIVE LOGITS
    참고
    0.49
     course
    0.46
     Bend
    0.41
     Coarse
    0.41
    dcc
    0.40
     Otter
    0.40
     démoc
    0.40
     endblock
    0.40
    ああ
    0.38
     COURSE
    0.38
    Activations Density 0.008%

    No Known Activations