© 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. 20-CLT-HP
    7. 75267
    Prev
    Next
    INDEX
    Explanations

    code and copyright notices

    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
    ScopeManager
    -0.50
     mukaan
    -0.47
    StoryboardSegue
    -0.47
    dată
    -0.41
    {{/
    -0.41
    PRWEB
    -0.40
    (/[
    -0.40
     årene
    -0.39
    IntoConstraints
    -0.39
    EndContext
    -0.39
    POSITIVE LOGITS
    TypedDataSet
    0.71
     a
    0.63
     A
    0.62
    tagHelperRunner
    0.59
    RTEE
    0.55
    webElementXpaths
    0.54
    WireFormat
    0.54
    scriptId
    0.54
    :
    0.53
    msgTypes
    0.52
    Activations Density 0.000%

    No Known Activations