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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39852
    Prev
    Next
    INDEX
    Explanations

    Errors, deviations, unusual circumstances

    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
    LookAnd
    -0.74
     enfans
    -0.70
     myſelf
    -0.69
     ویکی‌پدیا
    -0.66
    ztály
    -0.65
     décid
    -0.64
     ſhe
    -0.64
     ainfi
    -0.64
     enää
    -0.64
    клопе
    -0.63
    POSITIVE LOGITS
    بوابة
    0.56
    makeConstraints
    0.50
    er
    0.49
    e
    0.49
     certain
    0.49
     specific
    0.47
    GeneratedMessage
    0.46
    点
    0.44
    nte
    0.44
    te
    0.43
    Activations Density 0.043%

    No Known Activations