© 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. 1-CLT-HP
    7. 15277
    Prev
    Next
    INDEX
    Explanations

    Books and written material

    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
    TagHelper
    -0.79
    httphttps
    -0.73
     EconPapers
    -0.66
     @"/
    -0.65
     lenker
    -0.64
    SourceChecksum
    -0.60
    Искәрмәләр
    -0.55
     book
    -0.54
     Codex
    -0.54
    ValueStyle
    -0.53
    POSITIVE LOGITS
     Lijst
    0.57
     ögon
    0.56
    nyataan
    0.56
    Scénario
    0.56
    impulan
    0.56
     olvido
    0.56
    фикации
    0.55
     åt
    0.55
     facie
    0.55
     vergeten
    0.55
    Activations Density 0.011%

    No Known Activations