© 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. 9768
    Prev
    Next
    INDEX
    Explanations

    Diego

    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
     Diego
    -0.77
    MessageTagHelper
    -0.69
    tonsoft
    -0.69
    AndEndTag
    -0.68
     AspNetCore
    -0.63
    AutoresizingMask
    -0.61
    DoubleQuotes
    -0.59
     DIEGO
    -0.59
    CloseOperation
    -0.59
    ">//
    -0.58
    POSITIVE LOGITS
     medlemmer
    0.56
    ########.
    0.55
     nhiễm
    0.53
     szabály
    0.52
     /\.(
    0.52
    expandindo
    0.50
     Barlow
    0.49
     sottile
    0.49
    stanze
    0.49
    Хьажоргаш
    0.48
    Activations Density 0.008%

    No Known Activations