© 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. 2-RES-MATRYOSHKA-DC
    7. 6183
    Prev
    Next
    INDEX
    Explanations

    references to healthy or normal status

    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
    Not in Any Lists

    No Comments

    Negative Logits
     medical
    -0.79
    出版年
    -0.74
     Medical
    -0.70
    medical
    -0.69
     MEDICAL
    -0.67
    Medical
    -0.66
    MEDICAL
    -0.61
     emprego
    -0.60
     sanitarias
    -0.60
    uxxxx
    -0.59
    POSITIVE LOGITS
     healthy
    2.41
    healthy
    2.06
    Healthy
    2.05
     Healthy
    1.99
     healthiest
    1.59
     healthier
    1.48
     gesunde
    1.48
     saludable
    1.42
     unhealthy
    1.39
     saudável
    1.39
    Activations Density 0.011%

    No Known Activations