© 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. 993
    Prev
    Next
    INDEX
    Explanations

    references to antibody types and components involved in immune response

    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
    Personendaten
    -0.73
     дописавши
    -0.68
    ")));
    -0.67
    ',
    -0.66
     χρόν
    -0.65
    ̆
    -0.64
     :
    -0.63
     mergeFrom
    -0.63
     censiti
    -0.63
     AssemblyCompany
    -0.63
    POSITIVE LOGITS
     β
    1.41
     α
    1.40
    α
    1.38
    β
    1.38
    γ
    1.19
     μ
    1.14
     γ
    1.13
    μ
    1.08
     beta
    1.02
     alpha
    1.01
    Activations Density 0.408%

    No Known Activations