© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92105
    Prev
    Next
    INDEX
    Explanations

    Western

    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
    Not in Any Lists

    No Comments

    Negative Logits
     DMG
    -0.67
    ModelAdmin
    -0.63
     BIBLE
    -0.61
    httphttps
    -0.61
     unknownFields
    -0.61
     الرياضيه
    -0.61
     Wikispecies
    -0.57
    LCA
    -0.57
     utafiti
    -0.56
     getItemId
    -0.56
    POSITIVE LOGITS
     Esau
    0.53
     Australia
    0.42
     AssemblyTitle
    0.38
    por
    0.37
    ----+
    0.36
    AU
    0.36
    ffold
    0.35
    achu
    0.35
     Angelina
    0.35
     Alain
    0.34
    Activations Density 0.002%

    No Known Activations