© 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. 1149
    Prev
    Next
    INDEX
    Explanations

    references to immune responses and tumor-related processes

    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
     association
    -1.50
     ASSOCIATION
    -1.48
     Association
    -1.48
    Association
    -1.37
     associations
    -1.27
     Associations
    -1.23
    association
    -1.23
     Assn
    -1.18
     relationship
    -1.12
     Relationship
    -1.01
    POSITIVE LOGITS
     associated
    3.09
    associated
    2.70
    Associated
    2.19
     ASSOCIATED
    2.16
     Associated
    2.08
     related
    1.67
     accompanying
    1.66
     asociado
    1.53
     asociada
    1.52
     associé
    1.48
    Activations Density 0.317%

    No Known Activations