© 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. 321
    Prev
    Next
    INDEX
    Explanations

    references to multiple entities or concepts

    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
    abestanden
    -0.55
     rêves
    -0.55
     âmes
    -0.53
    IconModule
    -0.52
    VIAF
    -0.51
    Datuak
    -0.50
    thenReturn
    -0.50
     délais
    -0.49
     épaules
    -0.47
     frontières
    -0.47
    POSITIVE LOGITS
     several
    0.98
     many
    0.94
     MANY
    0.93
     dozens
    0.90
     Several
    0.84
     other
    0.82
    MANY
    0.82
     different
    0.82
     numerous
    0.81
     multiple
    0.81
    Activations Density 2.199%

    No Known Activations