© 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. 1105
    Prev
    Next
    INDEX
    Explanations

    Code/Technical 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
    <bos>
    -0.67
     revés
    -0.51
    FunctionFlags
    -0.50
     Not
    -0.49
    󠁢
    -0.48
     légère
    -0.48
    一方面
    -0.48
     not
    -0.48
    ’
    -0.48
     nifer
    -0.47
    POSITIVE LOGITS
    出版年
    0.63
     ExecuteAsync
    0.60
     createSlice
    0.60
    ForRow
    0.55
     Kaka
    0.54
     odkazy
    0.52
    fjspx
    0.52
     TextInputType
    0.51
    Obrázky
    0.50
    mschrijving
    0.50
    Activations Density 0.002%

    No Known Activations