© 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. 77966
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     '\\;'
    -0.80
     Reels
    -0.73
     internetowa
    -0.73
     reels
    -0.71
    şiv
    -0.70
    sizeCache
    -0.68
    ^(@)
    -0.68
     kaarangay
    -0.68
    ьаж
    -0.66
    zzarella
    -0.65
    POSITIVE LOGITS
     for
    0.41
     }{@
    0.36
     man
    0.36
    for
    0.36
     leksikon
    0.35
     Empieza
    0.34
     @"/
    0.33
    with
    0.33
     [*]
    0.32
    man
    0.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.