© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4877
    Prev
    Next
    INDEX
    Explanations

    references to medical treatment guidelines or recommendations

    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
     Guided
    -0.81
     guided
    -0.78
    guided
    -0.78
    Guided
    -0.77
     guiding
    -0.76
     guider
    -0.66
     Crusoe
    -0.64
    Джерела
    -0.63
     Guiding
    -0.62
     brancas
    -0.61
    POSITIVE LOGITS
     Guidelines
    2.25
     guidelines
    2.14
    Guidelines
    2.09
    guidelines
    1.95
     GUIDELINES
    1.79
     guideline
    1.72
     Guideline
    1.62
     Richtlinien
    0.93
     standards
    0.71
    ELINES
    0.71
    Activations Density 0.003%

    No Known Activations