© 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. 71636
    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
     saites
    -0.57
    Autoritní
    -0.55
     InputDecoration
    -0.55
     autorytatywna
    -0.55
    SharedDtor
    -0.53
     typelib
    -0.53
    сылкі
    -0.53
     تكبرها
    -0.53
    RenderAtEndOf
    -0.52
     AssemblyCulture
    -0.50
    POSITIVE LOGITS
    ąt
    0.53
     préf
    0.52
    Рис
    0.51
     Toute
    0.51
    啶
    0.50
     Switching
    0.50
     Aroma
    0.50
     pensieri
    0.49
     ngân
    0.48
     switching
    0.48
    Activations Density 0.003%

    No Known Activations