© 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. 6-RES-MATRYOSHKA-DC
    7. 1552
    Prev
    Next
    INDEX
    Explanations

    mentions of being exposed to something

    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
    MigrationBuilder
    -0.73
     lubrication
    -0.72
    writerow
    -0.71
    Carr
    -0.70
    thenia
    -0.70
    GraphicsUnit
    -0.67
     symboli
    -0.66
    ('/:
    -0.65
     rimb
    -0.65
    googleapis
    -0.65
    POSITIVE LOGITS
     exposure
    2.16
     Exposure
    1.99
    exposure
    1.98
     exposing
    1.86
     exposed
    1.85
    Exposure
    1.85
    Exposed
    1.84
     exposures
    1.81
     expose
    1.79
     Exposed
    1.78
    Activations Density 0.322%

    No Known Activations