© 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. 22-RES-MATRYOSHKA-DC
    7. 1588
    Prev
    Next
    INDEX
    Explanations

    text related to blood transfusions and transplant compatibility

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meanor
    -0.68
     '\\;'
    -0.60
    enumii
    -0.60
    phonie
    -0.58
    principalTable
    -0.55
     nahilalakip
    -0.54
    setOpen
    -0.54
    цездатний
    -0.51
     chi̍t
    -0.51
     InputDecoration
    -0.50
    POSITIVE LOGITS
     transplant
    1.45
     transplantation
    1.39
     donor
    1.38
     transplants
    1.34
     Transplantation
    1.34
     Transplant
    1.33
    transplant
    1.30
     Donor
    1.25
     transplanted
    1.24
     transplanting
    1.19
    Activations Density 0.784%

    No Known Activations