© 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. 1-CLT-HP
    7. 11669
    Prev
    Next
    INDEX
    Explanations

    to

    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
    key
    -0.54
    راق
    -0.51
    jsoup
    -0.50
    ुनिया
    -0.48
     
    -0.47
     key
    -0.46
    дай
    -0.45
    Key
    -0.45
    olini
    -0.45
    Expecting
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.84
    tvguidetime
    0.66
    titleMargin
    0.66
     EconPapers
    0.65
    exitRule
    0.64
    ')";
    0.64
     Normdatei
    0.64
    IVEREF
    0.63
     AssemblyCulture
    0.63
    )];
    0.62
    Activations Density 0.009%

    No Known Activations