© 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. 409
    Prev
    Next
    INDEX
    Explanations

    the word "patients" and words immediately preceding or following it that relate to medical diagnosis

    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
     Efq
    -0.95
     Chriftian
    -0.83
     Chrif
    -0.82
     Monfieur
    -0.82
    CompilerServices
    -0.81
     myſelf
    -0.77
    談社
    -0.75
     RIPRODUZIONE
    -0.74
     ſp
    -0.73
     Jefus
    -0.71
    POSITIVE LOGITS
     patients
    2.89
     Patients
    2.80
    Patients
    2.58
    patients
    2.50
     patient
    2.48
     Patient
    2.25
     pacientes
    2.17
    Patient
    2.16
    patient
    2.13
     PATIENT
    2.03
    Activations Density 0.635%

    No Known Activations