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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6011
    Prev
    Next
    INDEX
    Explanations

    mentions of healthcare mandates and insurance coverage, especially regarding birth control and religious exemptions.

    oai_token-act-pair · gemini-2.0-flash

    terms related to healthcare and insurance

    np_token-act-pair-logits · gpt-4o-mini

    Healthcare

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     RUSSELL
    -0.51
    tvguidetime
    -0.51
     kaarangay
    -0.51
    Bakgrunnsstoff
    -0.49
     Russell
    -0.47
    SuspendLayout
    -0.47
    SaveChangesAsync
    -0.47
    StoryboardSegue
    -0.46
     Ál
    -0.46
     BoxFit
    -0.46
    POSITIVE LOGITS
    yticks
    0.58
     cuidado
    0.57
     health
    0.56
     ComVisible
    0.53
    ACA
    0.52
     care
    0.52
     câble
    0.51
    HostException
    0.51
     relâche
    0.51
    etna
    0.51
    Activations Density 2.513%

    No Known Activations