© 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. 15289
    Prev
    Next
    INDEX
    Explanations

    code/formal writing, punctuation

    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
    Tikang
    -0.78
    mybatisplus
    -0.74
    VersionUID
    -0.73
    MLLoader
    -0.70
     surla
    -0.69
    хьтан
    -0.69
    Obrázky
    -0.67
     typelib
    -0.66
    MessageOf
    -0.66
     مشين
    -0.65
    POSITIVE LOGITS
    rippa
    0.50
     i
    0.49
     He
    0.49
     Gen
    0.48
     viz
    0.45
     Who
    0.43
    ↵↵
    0.43
     O
    0.41
     Acts
    0.40
     Himself
    0.40
    Activations Density 0.019%

    No Known Activations