© 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. 1-CLT-HP
    7. 10511
    Prev
    Next
    INDEX
    Explanations

    objective language

    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
     changé
    -0.59
     cambió
    -0.48
     amélior
    -0.48
     melhorar
    -0.48
     refroid
    -0.47
     gratuitement
    -0.47
     geçen
    -0.47
    こう
    -0.45
     changed
    -0.45
     vétérina
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.94
     EconPapers
    0.93
    AddTagHelper
    0.92
     الحره
    0.82
    GEBURTSDATUM
    0.82
     चीज़ों
    0.81
     kaarangay
    0.79
    
    0.79
     saites
    0.79
    NUMX
    0.79
    Activations Density 0.062%

    No Known Activations