© 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. 9718
    Prev
    Next
    INDEX
    Explanations

    formal texts

    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
     заре
    -0.47
    ipv
    -0.43
    gex
    -0.41
    pons
    -0.41
    ocytic
    -0.40
    সং
    -0.40
    heran
    -0.40
    bien
    -0.40
    WSTR
    -0.40
     अध्य
    -0.39
    POSITIVE LOGITS
    saraba
    0.71
     ExecuteAsync
    0.69
     CreateTagHelper
    0.68
     BoxDecoration
    0.68
    Referencie
    0.65
    Lähteet
    0.65
     Halley
    0.62
    ViewImports
    0.61
     PIECE
    0.60
     canter
    0.60
    Activations Density 0.002%

    No Known Activations