© 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. 96137
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
    GraphicsUnit
    -0.66
     VIAF
    -0.63
    VIAF
    -0.62
    sonaro
    -0.60
     verksamhet
    -0.59
     Casio
    -0.59
     artificiales
    -0.56
     Welles
    -0.55
    makeText
    -0.54
     Normdatei
    -0.54
    POSITIVE LOGITS
     “
    0.60
    ;*/
    0.57
     "}
    0.56
    kannya
    0.56
    ificity
    0.55
    ()");
    0.53
    */
    0.52
    λώ
    0.52
    agascar
    0.52
     her
    0.52
    Activations Density 0.017%

    No Known Activations