© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3449
    Prev
    Next
    INDEX
    Explanations

    language about regulations, particularly those related to safety, health, and economic competition

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    InjectAttribute
    -0.97
    bootstrapcdn
    -0.91
     CreateTagHelper
    -0.89
    setVerticalGroup
    -0.84
    djangoproject
    -0.84
    Tikang
    -0.77
    AccessorTable
    -0.76
    awtextra
    -0.76
    KommentareTeilen
    -0.73
    HasAnnotation
    -0.73
    POSITIVE LOGITS
    Patent
    0.56
    Trademark
    0.54
     licensing
    0.54
     Patent
    0.51
     Patents
    0.49
     Licensing
    0.46
     trademark
    0.46
     patent
    0.45
     patents
    0.45
    ία
    0.45
    Activations Density 1.783%

    No Known Activations