© 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. 4-CLT-HP
    7. 846
    Prev
    Next
    INDEX
    Explanations

    expression

    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
    ďaka
    -0.54
    trc
    -0.51
    сылкі
    -0.50
     démocratie
    -0.48
    corona
    -0.48
    lobby
    -0.48
     hennes
    -0.48
     navigable
    -0.47
     trône
    -0.46
     monographs
    -0.46
    POSITIVE LOGITS
     الحره
    0.65
    
    0.62
    Datuak
    0.61
     незавершена
    0.57
     nahilalakip
    0.57
    گان
    0.56
     <<<<<<<<<<<<<<
    0.54
    osoba
    0.54
    MemoryWarning
    0.52
    jsxFileName
    0.52
    Activations Density 0.000%

    No Known Activations