© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 303
    Prev
    Next
    INDEX
    Explanations

    references to biochemical research and experiments involving proteins and hormones

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     betweenstory
    -0.71
     <=",
    -0.59
    ⟬
    -0.57
     CreateTagHelper
    -0.52
    сылкі
    -0.52
    Hvem
    -0.52
    phosa
    -0.50
     AssemblyTitle
    -0.47
    ไหน
    -0.47
    udades
    -0.47
    POSITIVE LOGITS
    ensuremath
    0.51
     investigation
    0.40
    pubmed
    0.39
    ])).
    0.37
    ecap
    0.36
    netinet
    0.36
     medical
    0.35
     BERNAMA
    0.35
     human
    0.35
     Clinic
    0.35
    Activations Density 2.452%

    No Known Activations