© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3193
    Prev
    Next
    INDEX
    Explanations

    code-related

    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
     jspb
    -0.78
    yntaxException
    -0.78
    afficheront
    -0.76
     Walkover
    -0.74
    tyfik
    -0.74
     CURIAM
    -0.73
    RegressionTest
    -0.73
     الحره
    -0.70
    :✨
    -0.67
    isContained
    -0.66
    POSITIVE LOGITS
    agot
    0.44
    woon
    0.42
     électriques
    0.40
    sw
    0.37
     CreateTagHelper
    0.37
    seks
    0.36
    gez
    0.36
     Fitting
    0.35
    出版年
    0.34
    wer
    0.34
    Activations Density 0.003%

    No Known Activations