© 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. 0-RES-MATRYOSHKA-DC
    7. 11245
    Prev
    Next
    INDEX
    Explanations

    neurons related to specific immune cell types or states

    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
    twimg
    -0.75
    SharedDtor
    -0.66
    DockStyle
    -0.61
     intptr
    -0.58
     Abp
    -0.57
     виправивши
    -0.57
     Italijani
    -0.56
    <bos>
    -0.56
    RunAsync
    -0.55
    OGND
    -0.54
    POSITIVE LOGITS
     pleaſure
    0.62
    complexType
    0.58
     springfox
    0.57
     neighbours
    0.56
     niedersachsen
    0.55
    CELL
    0.54
     ſtate
    0.54
    DataAnnotations
    0.53
    phem
    0.53
    gwt
    0.52
    Activations Density 0.037%

    No Known Activations