© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4885
    Prev
    Next
    INDEX
    Explanations

    code

    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
     memen
    -0.42
     AssemblyTitle
    -0.42
     ReactDOM
    -0.42
     saken
    -0.40
     uintptr
    -0.39
    깥
    -0.36
    autoreleasepool
    -0.36
     reger
    -0.35
    unjang
    -0.35
    AccessFile
    -0.35
    POSITIVE LOGITS
    addCriterion
    0.72
    enumi
    0.70
    ScopeManager
    0.69
     CreateTagHelper
    0.66
    MethodManager
    0.64
     للاسماء
    0.64
     MenuView
    0.63
    tagHelperRunner
    0.61
     getC
    0.61
    AndEndTag
    0.60
    Activations Density 0.004%

    No Known Activations