© 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. 38860
    Prev
    Next
    INDEX
    Explanations

    diabetes

    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
     sugar
    -1.06
     diabetes
    -0.84
     Sugar
    -0.78
     sequence
    -0.77
    sugar
    -0.75
    sequence
    -0.66
     sucre
    -0.62
     Sequence
    -0.59
     secuencia
    -0.58
     azúcar
    -0.57
    POSITIVE LOGITS
    tagHelperRunner
    0.98
    ImageContext
    0.89
    LookAnd
    0.86
    parsedMessage
    0.86
     kaarangay
    0.84
    SourceChecksum
    0.83
     ***!
    0.81
     дописавши
    0.80
     >=",
    0.79
    IntoConstraints
    0.79
    Activations Density 0.235%

    No Known Activations