© 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. 1-RES-MATRYOSHKA-DC
    7. 110
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions related to blood clots, coagulation, and thrombosis

    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
     theſe
    -1.12
     ainfi
    -1.02
     thoſe
    -0.98
     rurale
    -0.96
     itſelf
    -0.96
     Eocene
    -0.94
     Viena
    -0.93
     României
    -0.92
     griega
    -0.91
     jesús
    -0.90
    POSITIVE LOGITS
     trans
    1.06
     Sw
    1.05
     Sk
    1.05
     Tra
    1.02
     chi
    1.02
     col
    1.00
     Ar
    0.98
     Sto
    0.98
     ro
    0.97
     sp
    0.96
    Activations Density 15.211%

    No Known Activations