© 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. 45551
    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
     
    -0.52
    .
    -0.37
    かし
    -0.34
     NOW
    -0.33
     mais
    -0.31
    例
    -0.30
     tanto
    -0.30
    сле
    -0.30
    Advertisement
    -0.29
    …
    -0.29
    POSITIVE LOGITS
     мәкал
    1.11
     "..\..\
    1.07
     itſelf
    1.06
     purpoſe
    1.02
     ddelweddau
    1.00
     uſed
    0.96
     ſeveral
    0.96
     myſelf
    0.95
    writeFieldEnd
    0.95
     ویکی‌پدی
    0.93
    Activations Density 0.030%

    No Known Activations