© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12984
    Prev
    Next
    INDEX
    Explanations

    how

    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
    __*/
    -0.71
    MessageOf
    -0.70
     Audiodateien
    -0.69
     cherchés
    -0.63
     समीक्षाएं
    -0.62
    interopRequire
    -0.61
     betrug
    -0.60
    Litter
    -0.60
    Посилання
    -0.58
    Numerology
    -0.58
    POSITIVE LOGITS
     ModelExpression
    0.62
     تضيفلها
    0.51
     HC
    0.47
    \{\\
    0.46
     الحره
    0.46
     folks
    0.45
    故
    0.44
     élu
    0.44
     to
    0.44
     instruction
    0.44
    Activations Density 0.004%

    No Known Activations