© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92156
    Prev
    Next
    INDEX
    Explanations

    Passion/enthusiasm

    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
     ſeveral
    -1.05
     myſelf
    -0.97
     greateſt
    -0.96
     fevere
    -0.95
     ſmall
    -0.92
     feveral
    -0.90
     vectorielles
    -0.90
     becauſe
    -0.88
     faſt
    -0.86
     Económica
    -0.85
    POSITIVE LOGITS
    <bos>
    1.06
    '
    0.60
     
    0.56
     it
    0.52
    y
    0.51
    er
    0.51
     and
    0.50
    ,
    0.50
    [
    0.50
    ’
    0.48
    Activations Density 0.203%

    No Known Activations