© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43126
    Prev
    Next
    INDEX
    Explanations

    taste

    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
     taste
    -1.73
     tasting
    -1.41
     Taste
    -1.36
    taste
    -1.36
    Taste
    -1.32
     tasted
    -1.27
    tasting
    -1.25
     tastes
    -1.24
     tast
    -1.19
     goût
    -0.90
    POSITIVE LOGITS
    AutoScaleMode
    0.73
     Majefty
    0.69
     myſelf
    0.62
    eep
    0.62
    TagMode
    0.60
     ſmall
    0.59
     itſelf
    0.59
    ByVersion
    0.57
     Plin
    0.57
     Perp
    0.57
    Activations Density 0.047%

    No Known Activations