© 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. 6198
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    NameInMap
    -0.84
     doubtnut
    -0.84
     saites
    -0.84
     ویکی‌آمباردا
    -0.81
    migrationBuilder
    -0.81
     tempered
    -0.79
     forgetting
    -0.79
    =$?
    -0.78
    
    -0.77
     recognising
    -0.75
    POSITIVE LOGITS
     parete
    0.50
     âmes
    0.47
     stället
    0.45
     jouets
    0.44
     générations
    0.44
     decorazione
    0.41
     dieux
    0.40
     courants
    0.39
     canaux
    0.38
     costuras
    0.38
    Activations Density 0.084%

    No Known Activations