© 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. 2-RES-MATRYOSHKA-DC
    7. 7708
    Prev
    Next
    INDEX
    Explanations

    references to medical doctors

    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
    </table>
    -0.58
    nbsp
    -0.56
    ‍♀️
    -0.56
    mergeFrom
    -0.56
     تانيه
    -0.52
     zog
    -0.52
     thousands
    -0.51
    anais
    -0.50
    ряда
    -0.50
     Neale
    -0.50
    POSITIVE LOGITS
     doctor
    2.22
    doctor
    2.08
     Doctor
    2.02
    Doctor
    1.99
     DOCTOR
    1.92
     Doctors
    1.91
     doctors
    1.86
    Doctors
    1.75
    doctors
    1.73
    DOCTOR
    1.66
    Activations Density 0.006%

    No Known Activations