© 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. 0-CLT-HP
    7. 40294
    Prev
    Next
    INDEX
    Explanations

    composition

    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
     composition
    -1.34
     pattern
    -1.08
    composition
    -1.03
     Composition
    -1.02
    Composition
    -0.97
     COMPOSITION
    -0.90
     composizione
    -0.89
    pattern
    -0.88
     composición
    -0.86
     configuration
    -0.84
    POSITIVE LOGITS
    ally
    0.76
    UpInside
    0.67
     betweenstory
    0.66
    SharedDtor
    0.65
     CreateTagHelper
    0.58
     onAnimation
    0.58
    KommentareTeilen
    0.56
    AndEndTag
    0.56
    MessageOf
    0.56
     ExecuteAsync
    0.56
    Activations Density 0.485%

    No Known Activations