© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92312
    Prev
    Next
    INDEX
    Explanations

    surgical procedures or gender gap

    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
     gap
    -1.25
     gaps
    -0.93
     Gap
    -0.82
    gaps
    -0.76
     Gaps
    -0.71
    gap
    -0.68
     room
    -0.67
    LookAnd
    -0.65
    Gap
    -0.64
     Quiz
    -0.61
    POSITIVE LOGITS
    a
    0.67
    ی
    0.67
    i
    0.65
     ویکی‌پدیا
    0.63
    o
    0.63
    e
    0.63
    y
    0.63
    ing
    0.56
    ي
    0.56
    ed
    0.55
    Activations Density 0.075%

    No Known Activations