© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1371
    Prev
    Next
    INDEX
    Explanations

    inflammation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    :\/\/
    -0.50
    copyWith
    -0.48
    kovsky
    -0.46
     inspired
    -0.46
     sitio
    -0.46
    فة
    -0.44
    gesetzt
    -0.44
     inspiration
    -0.44
    kull
    -0.42
     menudo
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.93
     autorytatywna
    0.90
    Personensuche
    0.87
    ArrowToggle
    0.85
    fjspx
    0.79
     Roskov
    0.79
     Wikimedijinoj
    0.77
     nahilalakip
    0.76
    featureID
    0.74
     Efq
    0.73
    Activations Density 0.001%

    No Known Activations