© 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. 99
    Prev
    Next
    INDEX
    Explanations

    specific medical terms and measurements related to health and infection

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.45
    *.
    -0.41
    **.
    -0.39
    °.
    -0.38
    !*\
    -0.38
     via
    -0.36
     unless
    -0.36
     private
    -0.35
    ™.
    -0.35
    .
    -0.35
    POSITIVE LOGITS
     is
    0.64
     zelve
    0.59
     ciertamente
    0.59
    pecabe
    0.58
    izacja
    0.58
     enseña
    0.58
     tė
    0.57
     كومونز
    0.56
    AndEndTag
    0.56
     Theſe
    0.56
    Activations Density 14.857%

    No Known Activations