© 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. 71451
    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
    Negative Logits
     roads
    -0.57
     highways
    -0.55
    heira
    -0.52
     faces
    -0.50
     링크
    -0.49
    postmedia
    -0.49
    Rujukan
    -0.48
     Roads
    -0.47
    TestMethod
    -0.47
    road
    -0.47
    POSITIVE LOGITS
    ьаж
    0.55
     nakalista
    0.54
    ⓧ
    0.54
    UpInside
    0.53
    LayoutPanel
    0.52
    PRET
    0.50
    يكب
    0.50
    pexpr
    0.50
    出版年
    0.50
     BoxFit
    0.48
    Activations Density 0.004%

    No Known Activations