© 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. 0-CLT-HP
    7. 43439
    Prev
    Next
    INDEX
    Explanations

    Consider

    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
    mo
    -0.91
     Consider
    -0.87
    Consider
    -0.77
    ale
    -0.70
    ThroughAttribute
    -0.68
     consideration
    -0.64
    addPreferredGap
    -0.63
    ALE
    -0.61
     HasFactory
    -0.60
     Consideration
    -0.60
    POSITIVE LOGITS
     the
    0.52
    oires
    0.48
    Produzione
    0.47
    ATELY
    0.47
     zasad
    0.46
    ebra
    0.46
    Tazama
    0.45
    estimated
    0.45
    yong
    0.45
    igt
    0.45
    Activations Density 0.105%

    No Known Activations