© 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. 5-CLT-HP
    7. 96158
    Prev
    Next
    INDEX
    Explanations

    Arguments or statements

    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
     démocr
    -0.69
     vœux
    -0.68
     âmes
    -0.66
     opérateur
    -0.65
     scolaires
    -0.64
     financières
    -0.64
     mauvaises
    -0.64
     églises
    -0.62
     spelar
    -0.62
     mêmes
    -0.61
    POSITIVE LOGITS
     that
    0.98
     the
    0.76
     Normdatei
    0.58
     rằng
    0.58
    bly
    0.57
    ably
    0.54
    VersionUID
    0.54
     relations
    0.52
    ties
    0.52
     ExecuteAsync
    0.52
    Activations Density 0.001%

    No Known Activations