© 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. 20-CLT-HP
    7. 78067
    Prev
    Next
    INDEX
    Explanations

    say "ous" endings

    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
    Negative Logits
    rungsseite
    -0.61
    PerformLayout
    -0.60
    StoryboardSegue
    -0.59
     jLabel
    -0.57
    Simplicity
    -0.56
     /\.(
    -0.56
     виправивши
    -0.55
    cipline
    -0.54
    piecze
    -0.52
    apimachinery
    -0.52
    POSITIVE LOGITS
    ous
    1.00
    rious
    0.88
    uous
    0.85
    ious
    0.85
    acious
    0.83
    rous
    0.83
    orous
    0.82
    urous
    0.79
    tious
    0.78
    cious
    0.74
    Activations Density 0.006%

    No Known Activations