Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14150
    Prev
    Next
    INDEX
    Explanations

    words related to surface characteristics of materials

    oai_token-act-pair · gemini-2.0-flash

    surface texture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.83
     pleaſure
    -0.82
     initComponents
    -0.79
    ConstraintMaker
    -0.78
     Italijanski
    -0.73
     houſe
    -0.73
     myſelf
    -0.73
    saraba
    -0.72
     flanking
    -0.72
     Paix
    -0.71
    POSITIVE LOGITS
     fine
    0.71
     pattern
    0.67
     texture
    0.62
    pattern
    0.59
     grain
    0.58
     por
    0.58
     Pattern
    0.56
    纹
    0.56
     micro
    0.55
     text
    0.54
    Activations Density 2.303%

    No Known Activations