© 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. 6268
    Prev
    Next
    INDEX
    Explanations

    still

    np_max-act · 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
    fjspx
    -0.57
    Enllaces
    -0.56
     betweenstory
    -0.54
    Šaltiniai
    -0.54
    guli
    -0.54
     estimés
    -0.54
     ModelExpression
    -0.53
     AssemblyTitle
    -0.52
    ItemBackground
    -0.51
     wiederholt
    -0.49
    POSITIVE LOGITS
     spacy
    0.70
    ISupport
    0.60
    InjectAttribute
    0.57
    uroy
    0.52
    httphttps
    0.50
     Esau
    0.49
     nõ
    0.49
     from
    0.48
     Bounty
    0.46
    imageshack
    0.46
    Activations Density 0.006%

    No Known Activations