© 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. 39932
    Prev
    Next
    INDEX
    Explanations

    monks, ale, and business

    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
     itſelf
    -1.33
     Efq
    -1.23
     myſelf
    -1.22
     Monfieur
    -1.14
     ―――――
    -1.13
     himſelf
    -1.13
     photolibrary
    -1.13
     ་་
    -1.12
     auroit
    -1.10
     feroit
    -1.09
    POSITIVE LOGITS
    s
    1.10
     
    0.75
    sz
    0.71
     in
    0.67
     at
    0.67
    sat
    0.65
     to
    0.64
    on
    0.63
     of
    0.61
     (
    0.60
    Activations Density 0.171%

    No Known Activations