© 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. 4-CLT-HP
    7. 4554
    Prev
    Next
    INDEX
    Explanations

    businesses

    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
     Walkover
    -0.53
     Readings
    -0.47
     Arra
    -0.47
    vra
    -0.46
     Rode
    -0.45
     Cuff
    -0.45
    Crossref
    -0.44
    illem
    -0.43
     Showers
    -0.43
     reader
    -0.43
    POSITIVE LOGITS
    <bos>
    1.28
    帖最后由
    0.67
    berdayakan
    0.62
     transfieras
    0.60
    '
    0.59
    ’
    0.59
     Offisielt
    0.57
    glGen
    0.56
     للمعارف
    0.56
     ejus
    0.56
    Activations Density 0.064%

    No Known Activations