© 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. 5-CLT-HP
    7. 91218
    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
    :✨
    -0.68
    @[+][
    -0.63
    ()][
    -0.53
     fossero
    -0.51
    jago
    -0.50
     harapan
    -0.50
    はじめに
    -0.50
     abbiano
    -0.50
     Sélectionnez
    -0.50
    畿
    -0.49
    POSITIVE LOGITS
     eman
    0.55
     resides
    0.55
     AppBar
    0.54
    ftagPool
    0.49
     inherent
    0.48
    AnimationsModule
    0.48
     resided
    0.48
    üstet
    0.48
     lies
    0.48
     to
    0.48
    Activations Density 0.000%

    No Known Activations