© 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. 71924
    Prev
    Next
    INDEX
    Explanations

    Code/unusual documents

    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
     sponsors
    -0.61
     questions
    -0.61
     classes
    -0.61
     posters
    -0.60
     examples
    -0.58
     topics
    -0.58
     videos
    -0.57
     songs
    -0.56
     pictures
    -0.56
     scenes
    -0.56
    POSITIVE LOGITS
    UserScript
    0.79
     jambes
    0.69
    apunov
    0.66
    yntaxException
    0.66
     wireType
    0.65
    клопе
    0.63
     Periodicals
    0.63
     Prom
    0.62
     Accounts
    0.61
    AddTagHelper
    0.61
    Activations Density 0.000%

    No Known Activations