© 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. 277
    Prev
    Next
    INDEX
    Explanations

    the prevalence and importance of the word "to" in various contexts

    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
     Majefty
    -0.49
     fubject
    -0.45
     habido
    -0.43
     fondamental
    -0.43
     stads
    -0.42
     hés
    -0.40
     getLayout
    -0.40
     currentValue
    -0.39
    分からない
    -0.39
     rés
    -0.39
    POSITIVE LOGITS
     to
    1.03
     To
    0.91
    To
    0.90
     να
    0.82
     TO
    0.80
    to
    0.80
     לה
    0.75
     ולה
    0.70
     să
    0.68
    是为了
    0.68
    Activations Density 1.366%

    No Known Activations