© 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. 20-CLT-HP
    7. 72722
    Prev
    Next
    INDEX
    Explanations

    code, urls, non-sentences

    np_max-act-logits · 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
    PositiveButton
    -0.51
    ecore
    -0.51
     Bonne
    -0.48
    Daphne
    -0.47
    spaceBetween
    -0.47
    aarrggbb
    -0.46
     manna
    -0.46
    Bonne
    -0.46
    selaer
    -0.46
     rist
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.66
     NDEBUG
    0.56
    AndEndTag
    0.54
    Życiorys
    0.49
    MessageTagHelper
    0.49
    Kaynakça
    0.48
     المعرف
    0.47
     agrí
    0.46
     endregion
    0.46
    ContentAsync
    0.45
    Activations Density 0.002%

    No Known Activations