© 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. 5-CLT-HP
    7. 92257
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    saraba
    -0.70
    zeera
    -0.53
    ensuremath
    -0.50
    perature
    -0.48
    getMinutes
    -0.48
    ifolia
    -0.48
     solida
    -0.48
    🦃
    -0.47
    inguém
    -0.47
    tisseur
    -0.47
    POSITIVE LOGITS
    RegistryLite
    0.63
    CppMethod
    0.61
     Процитовано
    0.61
    MarshalTo
    0.58
     <<<<<<<<<<<<<<
    0.57
     ब्रेकडाउन
    0.55
    DoubleQuotes
    0.55
    Cyfeiriadau
    0.54
     ویکی‌پدیا
    0.54
    setVerticalGroup
    0.54
    Activations Density 0.009%

    No Known Activations