© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94439
    Prev
    Next
    INDEX
    Explanations

    hyphens and slashes

    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
    州市
    -0.42
    down
    -0.40
    ↵↵
    -0.39
    CppCodeGen
    -0.38
     sobra
    -0.37
     ModelExpression
    -0.36
    ↵
    -0.35
    district
    -0.33
    over
    -0.32
    District
    -0.32
    POSITIVE LOGITS
    InjectAttribute
    0.85
    CloseOperation
    0.79
    Datuak
    0.75
     Normdatei
    0.73
    Activité
    0.72
    TargetException
    0.71
    
    0.69
     kaarangay
    0.69
    BeginContext
    0.67
    tisgarh
    0.67
    Activations Density 0.006%

    No Known Activations