© 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. 38967
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
     Y
    -0.45
    idosis
    -0.43
    er
    -0.42
     G
    -0.42
     createState
    -0.41
     &
    -0.40
    testng
    -0.40
    ick
    -0.40
    id
    -0.39
    ider
    -0.38
    POSITIVE LOGITS
    contentLoaded
    1.00
     الحره
    0.94
    makeConstraints
    0.91
     صوتيه
    0.86
    
    0.82
     استنادى
    0.79
    Lähteet
    0.75
    Personensuche
    0.75
    出版年
    0.75
    GEBURTSDATUM
    0.75
    Activations Density 0.142%

    No Known Activations