© 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. 77999
    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
    はじめに
    -0.81
    Into
    -0.68
    towards
    -0.65
     INTO
    -0.61
     Into
    -0.58
     Towards
    -0.58
    Towards
    -0.58
     towards
    -0.58
     reaching
    -0.57
    fromnode
    -0.56
    POSITIVE LOGITS
     to
    1.25
     calculées
    0.54
    Atsauces
    0.54
    MenuInflater
    0.50
     humaine
    0.47
     secund
    0.47
    kuuta
    0.46
     suffit
    0.45
    BeginContext
    0.45
     humaines
    0.45
    Activations Density 0.002%

    No Known Activations