© 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. 46048
    Prev
    Next
    INDEX
    Explanations

    Code/online 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
    lible
    -1.32
    corder
    -0.81
     AssemblyCulture
    -0.68
    ffindor
    -0.59
    তথ্যসূত্র
    -0.59
     umbi
    -0.52
    idane
    -0.52
     Signalez
    -0.52
    WebControls
    -0.51
    تقاوى
    -0.51
    POSITIVE LOGITS
    
    0.65
    enumi
    0.64
    XtraReports
    0.62
     cref
    0.54
     dbo
    0.53
    mobileqq
    0.52
    <![
    0.50
     Erscheinung
    0.49
    didSet
    0.49
     muualla
    0.49
    Activations Density 0.014%

    No Known Activations