© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92842
    Prev
    Next
    INDEX
    Explanations

    Dates

    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
    zież
    -0.57
    Lord
    -0.57
    ukone
    -0.57
    lord
    -0.56
    Portale
    -0.56
    LORD
    -0.56
    Stripe
    -0.55
     الاطلاع
    -0.55
    potranspiration
    -0.53
    sentry
    -0.52
    POSITIVE LOGITS
     فريبيس
    0.63
    OOTDTY
    0.52
    RTLR
    0.52
    Numerade
    0.50
    errHandler
    0.48
    +#+#
    0.48
    protoc
    0.47
    CloseOperation
    0.47
     بيها
    0.46
    posedge
    0.46
    Activations Density 0.001%

    No Known Activations