© 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. 20-CLT-HP
    7. 77559
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    np_max-act-logits · 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
    новништво
    -0.60
     leaſt
    -0.60
     muſt
    -0.58
     @"/
    -0.57
     ſhall
    -0.56
     theſe
    -0.56
     елның
    -0.56
    LEncoder
    -0.56
    Źródło
    -0.54
     Balik
    -0.53
    POSITIVE LOGITS
     nine
    0.53
     BrowserModule
    0.53
     NINE
    0.52
    mergeFrom
    0.49
    ctools
    0.49
    WebElementEntity
    0.48
    ServletException
    0.48
     eight
    0.47
    тию
    0.46
     betweenstory
    0.45
    Activations Density 0.001%

    No Known Activations