© 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. 138
    Prev
    Next
    INDEX
    Explanations

    elements related to biochemical compounds and their classifications

    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
    MessageOf
    -0.44
     lenker
    -0.43
    findpost
    -0.41
     PAPERS
    -0.40
     auft
    -0.40
    campista
    -0.40
     Irán
    -0.39
    CheckBreak
    -0.39
     parseFrom
    -0.38
     licences
    -0.38
    POSITIVE LOGITS
                                   
    0.72
    ----------------
    0.68
    ================
    0.59
    ffffffff
    0.59
    ————————————————
    0.58
    ****************
    0.57
    ................
    0.56
    ::::::::::::::::
    0.56
    ________________
    0.54
    ++++++++++++++++
    0.54
    Activations Density 0.696%

    No Known Activations