© 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. 7194
    Prev
    Next
    INDEX
    Explanations

    references to clinical outcomes and measures related to treatment response and patient prognosis

    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
     patient
    -1.49
     Patient
    -1.38
    patient
    -1.32
     PATIENT
    -1.31
    Patient
    -1.27
     clinical
    -1.15
    PATIENT
    -1.13
     paciente
    -1.05
     Clinical
    -1.02
     client
    -0.98
    POSITIVE LOGITS
    ופר
    0.54
     spad
    0.51
    essence
    0.49
    romyalgia
    0.49
    UCTION
    0.48
     persons
    0.48
    férence
    0.47
     siste
    0.47
    ことにしました
    0.47
     Wirth
    0.47
    Activations Density 0.036%

    No Known Activations