Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12542
    Prev
    Next
    INDEX
    Explanations

    chapter

    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
     ویکی‌پدیای
    -0.84
     Мексичка
    -0.74
    uxxxx
    -0.73
     تضيفلها
    -0.71
     חיצוניים
    -0.70
    thâu
    -0.69
    EndGlobalSection
    -0.68
     cherchés
    -0.68
     NSCoder
    -0.66
     mères
    -0.66
    POSITIVE LOGITS
     
    0.91
    -
    0.57
     III
    0.52
     opening
    0.49
     II
    0.49
    *
    0.49
      
    0.48
     VI
    0.47
    XmlAttribute
    0.47
    \
    0.47
    Activations Density 0.004%

    No Known Activations