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. 2120
    Prev
    Next
    INDEX
    Explanations

    the phrase "DC" (usually followed by another letter or abbreviation), likely related to "directed graph"

    oai_token-act-pair · gemini-2.0-flash

    DC

    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
     الحره
    -0.81
    IVEREF
    -0.75
    ########.
    -0.74
    DockStyle
    -0.67
    addCriterion
    -0.65
     ddelweddau
    -0.64
    uxxxx
    -0.62
     Мексичка
    -0.60
    InvalidProtocol
    -0.60
    ClientSize
    -0.60
    POSITIVE LOGITS
    না
    0.43
    ViewImports
    0.42
    ity
    0.42
    Toolkit
    0.41
    alto
    0.40
    wikidata
    0.39
    toolTip
    0.39
    cairn
    0.39
     minOccurs
    0.39
    TestingModule
    0.39
    Activations Density 0.874%

    No Known Activations