© 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. 2099
    Prev
    Next
    INDEX
    Explanations

    Course

    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
    Displays
    -0.38
    ftagPool
    -0.36
    íš
    -0.34
     femininas
    -0.34
    basicConfig
    -0.34
    Халык
    -0.32
    (&:
    -0.32
    się
    -0.31
    acuzzi
    -0.31
    bootstrapcdn
    -0.31
    POSITIVE LOGITS
     समीक्षाओं
    0.78
    
    0.76
    Vidite
    0.74
    hoeddwyd
    0.71
     AssemblyCulture
    0.71
     autorytatywna
    0.68
    WebElementEntity
    0.67
     EconPapers
    0.67
     ModelExpression
    0.67
    SourceChecksum
    0.67
    Activations Density 0.031%

    No Known Activations