© 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. 20-CLT-HP
    7. 76694
    Prev
    Next
    INDEX
    Explanations

    medical treatments

    np_max-act-logits · 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
    principalColumn
    -0.74
    
    -0.62
     مواليد
    -0.62
     ExecuteAsync
    -0.62
    تقاوى
    -0.57
    Jereo
    -0.57
    Сюжет
    -0.55
    gridx
    -0.54
    RegistryLite
    -0.54
     kasarigan
    -0.53
    POSITIVE LOGITS
    hysema
    0.51
     Zamora
    0.48
     setuptools
    0.47
    izacja
    0.47
     stopp
    0.45
     propOrder
    0.45
     ktorí
    0.45
     zä
    0.45
    FormTagHelper
    0.44
     förra
    0.44
    Activations Density 0.006%

    No Known Activations