© 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. 439
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in contexts implying capability or possibility

    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
     the
    -0.47
    y
    -0.44
     story
    -0.35
     fellow
    -0.35
     our
    -0.33
     in
    -0.33
     subject
    -0.33
     wise
    -0.32
     routine
    -0.32
    s
    -0.32
    POSITIVE LOGITS
     canst
    1.24
     can
    1.09
    Could
    0.98
    Can
    0.97
    could
    0.97
     ניתן
    0.96
    Bisa
    0.96
     COULD
    0.92
     Could
    0.91
    Podemos
    0.91
    Activations Density 1.207%

    No Known Activations