© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4963
    Prev
    Next
    INDEX
    Explanations

    references to the Dihydropyrimidine Dehydrogenase (DH) enzyme

    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
    UnusedPrivate
    -0.69
    XmlAccessType
    -0.66
     Armin
    -0.57
    ölf
    -0.55
     Schalke
    -0.49
    ingos
    -0.49
     deſ
    -0.48
    ADEL
    -0.48
     Jakarta
    -0.47
    ymal
    -0.47
    POSITIVE LOGITS
    DH
    3.47
     DH
    2.98
    dh
    2.30
     dh
    2.11
    Dh
    1.72
     Dh
    1.57
    DHA
    1.20
    BH
    1.05
    ADH
    0.99
     BH
    0.98
    Activations Density 0.004%

    No Known Activations