© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2836
    Prev
    Next
    INDEX
    Explanations

    Historical events/studies

    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
     visiteurs
    -0.55
     AspNetCore
    -0.51
    Visitor
    -0.51
     touristes
    -0.51
     Import
    -0.50
     Wikimedijinoj
    -0.50
     visitor
    -0.48
     import
    -0.48
    gart
    -0.48
     gelen
    -0.47
    POSITIVE LOGITS
    AccessorTable
    0.63
     <<<<<<<<<<<<<<
    0.61
    langkah
    0.58
     PRD
    0.57
    Geplaatst
    0.56
     Neander
    0.56
    ValueStyle
    0.54
     Cambo
    0.54
     Athenians
    0.54
     Transylvania
    0.54
    Activations Density 0.000%

    No Known Activations