© 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. 9330
    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
     a
    -1.12
     an
    -0.94
     the
    -0.90
     many
    -0.88
     some
    -0.84
     several
    -0.79
    many
    -0.73
     cérami
    -0.68
     ouvriers
    -0.68
     one
    -0.68
    POSITIVE LOGITS
    ⓧ
    0.77
     times
    0.68
    bootstrapcdn
    0.60
    出版年
    0.55
     Himo
    0.52
     kilos
    0.50
    évaluateur
    0.49
     metres
    0.48
     shots
    0.47
     fibres
    0.47
    Activations Density 0.351%

    No Known Activations