© 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. 16138
    Prev
    Next
    INDEX
    Explanations

    clothing

    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
     lady
    -1.04
     Lady
    -1.00
     LADY
    -0.96
    Lady
    -0.92
     gentleman
    -0.90
     shirt
    -0.87
    LADY
    -0.85
    lady
    -0.83
     shirts
    -0.75
     Shirt
    -0.71
    POSITIVE LOGITS
    local
    0.49
    tal
    0.46
    now
    0.44
    else
    0.43
    ful
    0.42
    land
    0.42
    no
    0.41
    coming
    0.41
    use
    0.41
    elastic
    0.41
    Activations Density 0.008%

    No Known Activations