© 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. 1-CLT-HP
    7. 9281
    Prev
    Next
    INDEX
    Explanations

    sex

    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
    ViewFeatures
    -0.52
     ویکی‌پدی
    -0.50
    ThroughAttribute
    -0.49
     recensement
    -0.47
    人民共和国
    -0.47
    jakan
    -0.47
     @"/
    -0.47
     varandra
    -0.45
     AssemblyProduct
    -0.45
     légales
    -0.44
    POSITIVE LOGITS
    iness
    0.75
    ็จ
    0.65
    pots
    0.63
     pooh
    0.62
    iest
    0.59
    shift
    0.59
    SourceChecksum
    0.57
    heads
    0.57
    surf
    0.57
     transférez
    0.55
    Activations Density 0.009%

    No Known Activations