© 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. 2161
    Prev
    Next
    INDEX
    Explanations

    Cap

    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
    ↵
    -0.42
    Capítulo
    -0.42
     (
    -0.42
    :
    -0.42
     x
    -0.41
    ×
    -0.39
     und
    -0.38
     and
    -0.37
    .
    -0.36
     dé
    -0.36
    POSITIVE LOGITS
    mybatisplus
    0.88
    Geplaatst
    0.88
     itſelf
    0.82
     initComponents
    0.78
    ſelves
    0.77
    ergies
    0.76
     تضيفلها
    0.75
    ніципалі
    0.75
     nahilalakip
    0.73
     surla
    0.73
    Activations Density 0.003%

    No Known Activations