© 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. 5-CLT-HP
    7. 94090
    Prev
    Next
    INDEX
    Explanations

    List selection programming

    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
    -0.79
    出版年
    -0.70
     BitmapFactory
    -0.68
    migrationBuilder
    -0.66
     kasarigan
    -0.65
    WindowConstants
    -0.62
    sizeCache
    -0.62
     onPage
    -0.62
    titleMargin
    -0.61
     viewDidLoad
    -0.60
    POSITIVE LOGITS
     box
    0.71
     Box
    0.58
     boxes
    0.57
    box
    0.52
    Box
    0.51
     Boxes
    0.51
    Boxes
    0.49
     boxe
    0.48
    boxes
    0.47
     âu
    0.45
    Activations Density 0.012%

    No Known Activations