© 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. 3209
    Prev
    Next
    INDEX
    Explanations

    words related to immune effector cells and signaling molecules involved in innate immunity

    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
     Süden
    -0.62
     зданий
    -0.60
    Referencer
    -0.59
    лізу
    -0.58
    гмента
    -0.58
     улице
    -0.57
    stände
    -0.56
     महत्व
    -0.56
    Спасылкі
    -0.56
    தை
    -0.56
    POSITIVE LOGITS
    ngdoc
    0.84
    bootstrapcdn
    0.84
    TypedDataSet
    0.76
    apunov
    0.76
     Impf
    0.72
    úgó
    0.71
    Slf
    0.67
     Italijanski
    0.66
     Prüf
    0.66
     sjuk
    0.66
    Activations Density 3.346%

    No Known Activations