© 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. 4686
    Prev
    Next
    INDEX
    Explanations

    eastern

    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
    aarrggbb
    -0.69
    SerializedName
    -0.63
    ValueStyle
    -0.61
     propOrder
    -0.57
    ArgsConstructor
    -0.56
    CDCl
    -0.55
    madonna
    -0.54
     leksikon
    -0.54
     gift
    -0.52
    devamını
    -0.52
    POSITIVE LOGITS
    saraba
    0.63
    ernalia
    0.59
     transfieras
    0.57
     DR
    0.55
    دانشنامهٔ
    0.51
     imaginar
    0.48
     Democratic
    0.48
    AndEndTag
    0.47
    CharStream
    0.47
    BASEPATH
    0.46
    Activations Density 0.003%

    No Known Activations