© 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. 12190
    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
     
    -0.56
    ↵↵↵
    -0.50
    ↵↵
    -0.50
    TITUDE
    -0.48
    сив
    -0.48
     c
    -0.47
    -
    -0.47
     imagining
    -0.47
     En
    -0.46
     asking
    -0.46
    POSITIVE LOGITS
    ScopeManager
    0.93
     purpoſe
    0.92
     createState
    0.90
    DeleteBehavior
    0.88
     itſelf
    0.86
     uſed
    0.84
    uxxxx
    0.83
     themſelves
    0.83
     pleaſure
    0.82
     reaſon
    0.81
    Activations Density 0.018%

    No Known Activations