© 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. 16248
    Prev
    Next
    INDEX
    Explanations

    neurology

    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
    uisine
    -0.59
     formula
    -0.50
     okuyayım
    -0.49
     Greenberg
    -0.49
    اجة
    -0.48
    ATED
    -0.48
    ALLY
    -0.47
    ramide
    -0.47
    ardige
    -0.47
     العلاقات
    -0.47
    POSITIVE LOGITS
     صوتيه
    0.85
    setof
    0.56
     anglès
    0.56
     esternos
    0.54
     consultato
    0.53
     inglesa
    0.53
     doInBackground
    0.52
     sonno
    0.50
     Poincar
    0.50
    GIVEREF
    0.50
    Activations Density 0.021%

    No Known Activations