© 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. 1246
    Prev
    Next
    INDEX
    Explanations

    contribution

    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
     contributions
    -1.83
     Contributions
    -1.83
     Contribution
    -1.79
     contribution
    -1.76
    Contribution
    -1.67
    contribution
    -1.62
     CONTRIBUTIONS
    -1.56
     CONTRIBUTION
    -1.55
    Contributions
    -1.52
    contributions
    -1.45
    POSITIVE LOGITS
     to
    0.58
     it
    0.57
    ment
    0.52
     man
    0.48
     grade
    0.48
    ец
    0.47
    e
    0.47
    enterOuterAlt
    0.45
     ten
    0.45
     Grade
    0.45
    Activations Density 0.154%

    No Known Activations