© 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. 12242
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ModelAdmin
    -0.61
     itſelf
    -0.50
     Torr
    -0.48
    untitled
    -0.47
    atility
    -0.46
    geren
    -0.46
     Huguen
    -0.46
    islation
    -0.46
     fathoms
    -0.46
     varandra
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.68
     this
    0.63
    jsxFileName
    0.63
     any
    0.62
     all
    0.62
    course
    0.60
    Demografía
    0.57
    ThroughAttribute
    0.56
     different
    0.55
    ÍN
    0.54
    Activations Density 0.005%

    No Known Activations