© 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. 264
    Prev
    Next
    INDEX
    Explanations

    phrases questioning the nature of things or seeking clarification

    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
    FunctionFlags
    -0.58
     disambiguazione
    -0.56
    sidemargin
    -0.54
    ьажоргаш
    -0.51
    idated
    -0.51
    ⓧ
    -0.50
     uitz
    -0.50
    Cyfarwyddwr
    -0.50
    UnusedPrivate
    -0.49
    SPJ
    -0.48
    POSITIVE LOGITS
     what
    1.15
    what
    1.00
     WHAT
    0.96
     What
    0.94
    What
    0.91
    WHAT
    0.84
     whats
    0.81
    whats
    0.79
     things
    0.69
     thing
    0.68
    Activations Density 1.395%

    No Known Activations