© 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. 0-CLT-HP
    7. 1180
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
     "
    -0.95
     “
    -0.81
     (
    -0.71
     supp
    -0.59
     lat
    -0.58
     the
    -0.57
     all
    -0.57
     complete
    -0.57
     demo
    -0.56
     Ger
    -0.56
    POSITIVE LOGITS
     avoient
    0.79
     незавершена
    0.79
     neceffary
    0.78
     comigo
    0.74
     quelcon
    0.73
     étoient
    0.73
     itſelf
    0.71
     uſed
    0.69
     auffi
    0.69
     impractica
    0.69
    Activations Density 0.259%

    No Known Activations