© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6180
    Prev
    Next
    INDEX
    Explanations

    a

    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
    Negative Logits
    oules
    -0.60
     zvlá
    -0.49
     onView
    -0.49
    oció
    -0.47
     Tenis
    -0.47
    Становништво
    -0.47
    あるので
    -0.45
    seitige
    -0.45
    ʲ
    -0.44
     Toko
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.84
    tagHelperRunner
    0.76
     المعيارى
    0.67
     snippetHide
    0.64
    execSQL
    0.63
    MLLoader
    0.62
    FunctionFlags
    0.62
     noDo
    0.60
    interopRequire
    0.60
     transfieras
    0.59
    Activations Density 0.004%

    No Known Activations