© 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. 94781
    Prev
    Next
    INDEX
    Explanations

    legacy

    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
     broken
    -2.36
    broken
    -2.13
     broke
    -1.98
     Broken
    -1.85
     breaking
    -1.80
    Broken
    -1.79
     breaks
    -1.78
    broke
    -1.66
    breaking
    -1.60
     Breaks
    -1.50
    POSITIVE LOGITS
    complexType
    0.59
    $/,
    0.56
    церт
    0.56
    낼
    0.55
    çek
    0.53
    wij
    0.49
    delaire
    0.49
    ClientSize
    0.47
    piel
    0.46
    HttpServlet
    0.46
    Activations Density 0.064%

    No Known Activations