© 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. 1003
    Prev
    Next
    INDEX
    Explanations

    Rules, procedures, navigation

    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
    InputBorder
    -0.68
     InputDecoration
    -0.66
     فريبيس
    -0.65
    
    -0.63
    :✨
    -0.63
    AndEndTag
    -0.62
    InputTagHelper
    -0.62
    <<<<
    -0.61
    GEBURTSDATUM
    -0.60
    migrationBuilder
    -0.60
    POSITIVE LOGITS
     pageContext
    0.52
     consecrated
    0.51
     sac
    0.48
    fromCharCode
    0.46
     framed
    0.46
    czaj
    0.45
     cher
    0.42
    preventDefault
    0.42
    RTSC
    0.42
     enshrined
    0.42
    Activations Density 0.003%

    No Known Activations