© 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. 0-CLT-HP
    7. 41677
    Prev
    Next
    INDEX
    Explanations

    Horne

    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
     humains
    -0.60
     mécan
    -0.57
     colorés
    -0.56
     chimiques
    -0.55
     positifs
    -0.54
     asupra
    -0.53
     naturelles
    -0.53
     relatifs
    -0.53
     richiede
    -0.53
     rechange
    -0.52
    POSITIVE LOGITS
    
    0.84
     EconPapers
    0.81
    DockStyle
    0.73
     ويكيميديا
    0.72
    UnsafeEnabled
    0.72
     متعلقه
    0.70
    LLocation
    0.69
    WidgetItem
    0.68
    uxxxx
    0.65
    клопе
    0.64
    Activations Density 0.495%

    No Known Activations