© 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. 1-CLT-HP
    7. 746
    Prev
    Next
    INDEX
    Explanations

    electrical circuits

    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
     elettrica
    -0.52
     enfans
    -0.47
    AndEndTag
    -0.47
     elect
    -0.47
    Descripció
    -0.46
     ویکی‌پدیای
    -0.45
    ="<?=$
    -0.44
    \",\"
    -0.44
    methe
    -0.43
     muse
    -0.42
    POSITIVE LOGITS
    MLLoader
    0.59
    TintMode
    0.56
    tisol
    0.55
     ExecuteAsync
    0.55
     localObject
    0.52
     Thess
    0.52
    chenkt
    0.52
    poons
    0.51
    CPtr
    0.51
    HasAnnotation
    0.51
    Activations Density 0.049%

    No Known Activations