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. 14053
    Prev
    Next
    INDEX
    Explanations

    violent actions resulting in physical harm

    oai_token-act-pair · gemini-2.0-flash

    landing

    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
     Normdatei
    -0.81
    原始内容存档于
    -0.79
     ujednoznacz
    -0.73
     lenker
    -0.72
     autorytatywna
    -0.71
     kasarigan
    -0.68
    ArgsConstructor
    -0.68
    RegressionTest
    -0.68
    setVerticalGroup
    -0.65
    AntiForgeryToken
    -0.65
    POSITIVE LOGITS
     landed
    0.56
     landing
    0.56
     hits
    0.47
     lands
    0.47
    Landing
    0.45
    borderBottom
    0.43
    からは
    0.42
     hitting
    0.42
     crashes
    0.41
     noise
    0.41
    Activations Density 2.009%

    No Known Activations