© 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. 20-CLT-HP
    7. 75314
    Prev
    Next
    INDEX
    Explanations

    drink

    np_max-act-logits · 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
    sizeCache
    -1.01
     متعلقه
    -0.93
     propOrder
    -0.81
    OGND
    -0.78
     AssemblyTitle
    -0.69
    rawDesc
    -0.69
    elemField
    -0.68
    awtextra
    -0.68
    ftagPool
    -0.67
    AnimationsModule
    -0.66
    POSITIVE LOGITS
     Drink
    0.57
     DRINK
    0.56
     Drinking
    0.55
    Drinking
    0.50
     drinking
    0.49
    Drink
    0.47
     si
    0.45
     DEAD
    0.45
     drinkers
    0.44
     Hola
    0.43
    Activations Density 0.000%

    No Known Activations