© 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. 42804
    Prev
    Next
    INDEX
    Explanations

    avoid

    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
     avoided
    -2.27
     avoid
    -2.02
     avoids
    -1.91
     Avoid
    -1.83
    Avoid
    -1.75
    avoid
    -1.66
     avoidance
    -1.66
     Avoidance
    -1.57
     Avoiding
    -1.56
     évit
    -1.54
    POSITIVE LOGITS
     being
    0.70
    出版年
    0.66
    StructEnd
    0.59
     having
    0.59
     becoming
    0.58
    はじめに
    0.58
     finding
    0.58
     eating
    0.57
    posedge
    0.56
     making
    0.54
    Activations Density 1.428%

    No Known Activations