© 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. 71299
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
     PTS
    -0.57
    Lumi
    -0.54
     Zet
    -0.54
     firebaseConfig
    -0.54
    laten
    -0.51
     Renaissance
    -0.50
     Lumi
    -0.49
     Zinn
    -0.49
    TagHelper
    -0.49
     Rat
    -0.49
    POSITIVE LOGITS
    principalTable
    0.61
     Reverso
    0.55
     المعيارى
    0.54
     NSCoder
    0.54
    .*")]
    0.53
     lenker
    0.53
    PreferredItem
    0.52
    tagHelperRunner
    0.52
    Autoritní
    0.50
    istible
    0.49
    Activations Density 0.000%

    No Known Activations