© 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. 2867
    Prev
    Next
    INDEX
    Explanations

    code/math snippets

    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
    MemoryWarning
    -0.70
     ModelExpression
    -0.66
    Geplaatst
    -0.65
    MethodManager
    -0.62
     مرئيه
    -0.59
    AddTagHelper
    -0.55
    istoitu
    -0.52
     AssemblyCulture
    -0.50
    DropColumn
    -0.50
    NameInMap
    -0.50
    POSITIVE LOGITS
    DoubleQuotes
    0.61
    MLLoader
    0.61
    OGND
    0.59
     للاسماء
    0.58
    |}{$
    0.57
    clerview
    0.52
     AssemblyProduct
    0.52
    OOTDTY
    0.52
    APORE
    0.52
     StatefulWidget
    0.52
    Activations Density 0.121%

    No Known Activations