© 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. 11681
    Prev
    Next
    INDEX
    Explanations

    programming arguments/variables

    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
     &'
    -0.55
    wagen
    -0.52
    nl
    -0.50
    wä
    -0.47
     parte
    -0.45
     Lordship
    -0.45
    criminator
    -0.44
    ukov
    -0.43
    ienen
    -0.42
     Bal
    -0.42
    POSITIVE LOGITS
    AddTagHelper
    0.95
    دانشنامهٔ
    0.71
     مرئيه
    0.70
    uxxxx
    0.68
     GenerationType
    0.67
    AutoresizingMask
    0.65
    CloseOperation
    0.64
    Hochspringen
    0.62
     EconPapers
    0.61
    setVerticalGroup
    0.61
    Activations Density 0.019%

    No Known Activations