© 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. 39930
    Prev
    Next
    INDEX
    Explanations

    WC

    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
    MemoryWarning
    -0.62
    routeProvider
    -0.59
     Bad
    -0.56
     onOptions
    -0.53
    singing
    -0.52
    ects
    -0.50
    defineProperty
    -0.50
    phazard
    -0.49
    buttonShape
    -0.48
     sang
    -0.48
    POSITIVE LOGITS
     Monfieur
    0.79
     lordship
    0.76
     becauſe
    0.75
     Houſe
    0.73
     Anſ
    0.73
     Phry
    0.71
     fathoms
    0.71
     ARIA
    0.70
     Pelop
    0.69
     Efq
    0.69
    Activations Density 0.119%

    No Known Activations