© 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. 71549
    Prev
    Next
    INDEX
    Explanations

    genealogy

    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
     MainAxisSize
    -0.63
     Vip
    -0.61
    tvguidetime
    -0.60
    izational
    -0.56
    MLLoader
    -0.55
     localObject
    -0.54
     Nieren
    -0.54
    onnay
    -0.54
     roe
    -0.53
     protoimpl
    -0.52
    POSITIVE LOGITS
    LinkId
    0.56
     chuẩn
    0.54
     he
    0.54
    he
    0.52
    httphttps
    0.52
    H
    0.51
    他才
    0.50
     pinulongan
    0.50
     dec
    0.49
     levure
    0.49
    Activations Density 0.001%

    No Known Activations