© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    medical terminology, especially those related to inflammatory response and genetics, often in the context of research studies.

    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
    aarrggbb
    -0.64
    forChild
    -0.60
    rungsseite
    -0.58
    +#+
    -0.56
    WebServlet
    -0.52
    Naissance
    -0.52
     Claudius
    -0.52
     typelib
    -0.51
    EndContext
    -0.49
    matchCondition
    -0.48
    POSITIVE LOGITS
     inflammation
    1.27
     Inflammation
    1.24
     inflammatory
    1.23
     Inflammatory
    1.22
     infla
    1.20
     Infla
    1.16
    Infla
    1.16
    lammatory
    1.15
    inflammation
    1.13
    inflammatory
    1.10
    Activations Density 1.352%

    No Known Activations