© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 185
    Prev
    Next
    INDEX
    Explanations

    words related to improving healthcare practices and quality, and reorganizing healthcare systems

    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/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.70
     تانيه
    -0.65
    djangoproject
    -0.63
     naturelles
    -0.63
     оригіналу
    -0.62
     Properties
    -0.59
     moul
    -0.58
     PROPERTIES
    -0.57
    iedades
    -0.57
     unplayable
    -0.56
    POSITIVE LOGITS
     medical
    1.30
     hospital
    1.26
     patient
    1.24
     clinical
    1.23
     hospitals
    1.20
     healthcare
    1.19
     Medical
    1.16
     patients
    1.14
     clinic
    1.12
     clinics
    1.12
    Activations Density 3.453%

    No Known Activations