© 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. 1-RES-MATRYOSHKA-DC
    7. 1300
    Prev
    Next
    INDEX
    Explanations

    mentions of sexual activity or related concepts

    oai_token-act-pair · gpt-4.1-nano
    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
    SharedDtor
    -0.70
     Italijani
    -0.63
     Италијани
    -0.61
    migrationBuilder
    -0.58
     unknownFields
    -0.57
     '\\;'
    -0.57
    ыгана
    -0.55
    endenza
    -0.55
    ']").
    -0.55
    MigrationBuilder
    -0.54
    POSITIVE LOGITS
     sex
    3.81
     Sex
    3.48
     sexual
    3.33
    Sex
    3.33
     SEX
    3.30
    sex
    3.25
     Sexual
    3.08
    SEX
    3.02
    sexual
    2.94
    Sexual
    2.89
    Activations Density 0.606%

    No Known Activations