© 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. 0-CLT-HP
    7. 94399
    Prev
    Next
    INDEX
    Explanations

    Vall

    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
    ########.
    -0.69
    ament
    -0.57
    IMENTS
    -0.57
     Vall
    -0.56
    zsche
    -0.56
    ement
    -0.55
    amento
    -0.55
    ama
    -0.54
    UserScript
    -0.52
    letoe
    -0.50
    POSITIVE LOGITS
     fidélité
    0.54
     eenige
    0.52
     dignité
    0.51
     vantaggi
    0.50
     abenço
    0.50
     handen
    0.48
    Vorteile
    0.48
     Disadvantages
    0.48
    enguaje
    0.48
    entai
    0.48
    Activations Density 1.846%

    No Known Activations