© 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. 1-CLT-HP
    7. 45619
    Prev
    Next
    INDEX
    Explanations

    insurance

    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
     insurance
    -0.95
     Insurance
    -0.87
     INSURANCE
    -0.85
    Insurance
    -0.78
     Италијани
    -0.77
    Geplaatst
    -0.70
    insurance
    -0.70
    المناصب
    -0.70
     propOrder
    -0.68
    ollectionView
    -0.67
    POSITIVE LOGITS
    ificantly
    0.52
    izowane
    0.52
     виправивши
    0.47
    IPE
    0.47
    AutoScaleMode
    0.45
    Datuak
    0.45
    TRIP
    0.45
    iloj
    0.44
    esterday
    0.44
    tschaft
    0.44
    Activations Density 0.175%

    No Known Activations