© 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. 4-CLT-HP
    7. 3390
    Prev
    Next
    INDEX
    Explanations

    and

    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
    '
    -0.45
    krat
    -0.40
    bacillus
    -0.39
     izan
    -0.37
    raulic
    -0.37
    lasma
    -0.37
    ł
    -0.36
    eak
    -0.36
    warts
    -0.35
    mol
    -0.35
    POSITIVE LOGITS
    حياته
    0.72
     ***!
    0.71
    ArrowToggle
    0.69
     "..\..\..\
    0.69
     contextLoads
    0.68
     }{@
    0.66
    aarrggbb
    0.64
     isInitialized
    0.63
    endphp
    0.63
    حياتها
    0.62
    Activations Density 0.006%

    No Known Activations