© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 346
    Prev
    Next
    INDEX
    Explanations

    statements that express opinions or claims and their supporting evidence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     TestBed
    -0.49
    TargetException
    -0.46
    autant
    -0.45
     ब्रेकडाउन
    -0.45
     volna
    -0.44
    Bibliote
    -0.44
     vloer
    -0.44
    GeoNames
    -0.44
     Peshawar
    -0.43
     Poplar
    -0.43
    POSITIVE LOGITS
     that
    0.69
     rằng
    0.68
     saying
    0.57
     bahwa
    0.57
     said
    0.54
    说
    0.53
    GEBURTSDATUM
    0.53
     SAYS
    0.52
     mengatakan
    0.52
     says
    0.52
    Activations Density 3.227%

    No Known Activations