© 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. 358
    Prev
    Next
    INDEX
    Explanations

    chemical structures or formulas

    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
     تضيفلها
    -0.60
     indisponible
    -0.57
     '\\;'
    -0.56
    +#+
    -0.55
    DIPSETTING
    -0.54
    AccessorTable
    -0.54
    ंदीखरीदारी
    -0.52
    帖最后由
    -0.52
     Chwiliwch
    -0.52
    OGND
    -0.50
    POSITIVE LOGITS
    meck
    0.41
     Twin
    0.40
     element
    0.40
    mrc
    0.39
    ayage
    0.38
    ⮕
    0.38
    にした
    0.38
     coti
    0.38
    Twin
    0.38
    '}>
    0.38
    Activations Density 2.405%

    No Known Activations