© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16065
    Prev
    Next
    INDEX
    Explanations

    drinks

    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
    Negative Logits
     drinks
    -0.94
     Drinks
    -0.79
    Drinks
    -0.74
    drinks
    -0.66
     Getränke
    -0.54
    drink
    -0.53
     ainfi
    -0.52
     Vorder
    -0.52
     auffi
    -0.51
     drink
    -0.51
    POSITIVE LOGITS
     للاسماء
    0.82
     '\\;'
    0.53
    DoubleQuotes
    0.52
    Carrière
    0.51
    setVerticalGroup
    0.50
    autique
    0.48
     chaff
    0.47
    úgó
    0.47
    IsContent
    0.46
     NUKAT
    0.45
    Activations Density 0.006%

    No Known Activations