© 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. 1-CLT-HP
    7. 16018
    Prev
    Next
    INDEX
    Explanations

    countries

    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
    SequentialGroup
    -0.66
     combineReducers
    -0.65
     مشين
    -0.63
    getDescriptor
    -0.59
    OrBuilder
    -0.57
    setContentView
    -0.57
    Itoa
    -0.57
    رشف
    -0.57
     gynhyrchwyd
    -0.57
     Commencez
    -0.56
    POSITIVE LOGITS
    setVerticalGroup
    0.46
    rogenic
    0.41
    Treatment
    0.40
    uría
    0.40
     côtes
    0.39
    wortet
    0.39
    ویت
    0.38
    OHN
    0.38
    esso
    0.38
    ريط
    0.38
    Activations Density 0.002%

    No Known Activations