© 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. 5-CLT-HP
    7. 98124
    Prev
    Next
    INDEX
    Explanations

    from

    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
    IntoConstraints
    -0.54
    PositiveButton
    -0.46
    principalColumn
    -0.43
    prepareStatement
    -0.41
    instancetype
    -0.41
    cresc
    -0.40
     looking
    -0.40
     finding
    -0.39
     demais
    -0.39
    kheim
    -0.37
    POSITIVE LOGITS
    الحياه
    0.77
    ValueGeneration
    0.74
    aarrggbb
    0.72
    олові
    0.71
     a
    0.68
    ándalo
    0.68
    Hauptartikel
    0.67
    WithIOException
    0.67
    Архівовано
    0.63
    rungsseite
    0.63
    Activations Density 0.002%

    No Known Activations