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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16360
    Prev
    Next
    INDEX
    Explanations

    code related to web programming

    oai_token-act-pair · gemini-2.0-flash

    web application code

    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
    rungsseite
    -0.56
    CopyWith
    -0.56
     okuyayım
    -0.52
    AndroidJUnit
    -0.49
    getDescriptor
    -0.49
    sizeCache
    -0.49
    mení
    -0.49
    IContainer
    -0.48
    /*
    -0.47
    interopRequire
    -0.46
    POSITIVE LOGITS
    Hentet
    0.69
     AssemblyCulture
    0.60
    Diwedd
    0.59
    التالي
    0.59
    ificent
    0.58
    ssymb
    0.57
    Immobili
    0.57
    essura
    0.56
    Zunanje
    0.56
    houette
    0.55
    Activations Density 0.053%

    No Known Activations