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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41375
    Prev
    Next
    INDEX
    Explanations

    sugar

    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
    -1.02
    sugar
    -1.01
     Sugar
    -0.83
     SUGAR
    -0.77
    Sugar
    -0.77
     azúcar
    -0.72
    Rüyada
    -0.72
     sugars
    -0.70
    sug
    -0.69
    ρίς
    -0.69
    POSITIVE LOGITS
    bootstrapcdn
    0.52
    #
    0.48
    
    0.46
    .
    0.43
     bur
    0.42
     fries
    0.42
     monoxide
    0.41
    like
    0.41
     sets
    0.41
     dormitorio
    0.40
    Activations Density 0.237%

    No Known Activations