© 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. 1-CLT-HP
    7. 10937
    Prev
    Next
    INDEX
    Explanations

    catal

    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
     Caused
    -0.62
     Chwiliwch
    -0.56
    Cause
    -0.55
    Caus
    -0.52
    WireFormatLite
    -0.52
    VersionUID
    -0.52
    UrlResolution
    -0.52
    ServletException
    -0.51
    لمات
    -0.51
    ReusableCell
    -0.51
    POSITIVE LOGITS
     Maxima
    0.63
     يتيمه
    0.60
     oreille
    0.54
    zation
    0.53
     Accident
    0.52
    izer
    0.52
     punte
    0.52
     Healey
    0.51
     préoccup
    0.50
     Harms
    0.50
    Activations Density 0.007%

    No Known Activations