© 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. 3-RES-MATRYOSHKA-DC
    7. 2124
    Prev
    Next
    INDEX
    Explanations

    the phrase "metabolic syndrome" or just the word "syndrome" in a medical context

    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
    Not in Any Lists

    No Comments

    Negative Logits
     charité
    -0.60
     détach
    -0.59
     megh
    -0.57
    pable
    -0.56
    ambi
    -0.56
    Рабо
    -0.56
     Scritto
    -0.56
    tug
    -0.55
     LOG
    -0.55
     Рабо
    -0.55
    POSITIVE LOGITS
     syndrome
    3.33
     Syndrome
    3.05
     syndromes
    2.48
    ndrome
    2.25
     síndrome
    1.73
     Synd
    1.59
     синд
    1.56
     synd
    1.40
    Synd
    1.23
    synd
    1.23
    Activations Density 0.006%

    No Known Activations