© 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. 94885
    Prev
    Next
    INDEX
    Explanations

    juice or ribbon

    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
     juices
    -1.52
     juice
    -1.47
    juice
    -1.30
     Juice
    -1.13
    Juice
    -1.04
     ribbon
    -0.94
     ribbons
    -0.77
     Ribbon
    -0.73
     JU
    -0.68
    ribbon
    -0.66
    POSITIVE LOGITS
     ModelExpression
    0.56
    ir
    0.54
    AutoField
    0.53
     onPage
    0.52
     Fowler
    0.50
    EnableWeb
    0.50
     fédé
    0.50
     صوتيه
    0.50
    ed
    0.50
    autoconfigure
    0.49
    Activations Density 1.587%

    No Known Activations