© 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. 44182
    Prev
    Next
    INDEX
    Explanations

    research topics

    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
    ArgsConstructor
    -0.98
    出版年
    -0.93
     <>",
    -0.92
     doInBackground
    -0.89
    voorbeeld
    -0.88
    GraphicsUnit
    -0.88
     vícti
    -0.88
     mauva
    -0.87
     fidélité
    -0.86
     nôtre
    -0.83
    POSITIVE LOGITS
     number
    0.54
    nog
    0.54
     ghi
    0.50
     double
    0.47
     second
    0.45
     extra
    0.45
     matter
    0.43
    ,
    0.43
     record
    0.43
     and
    0.43
    Activations Density 0.060%

    No Known Activations