© 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. 166
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or characters in a narrative context

    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
     تعدى
    -0.59
    expandindo
    -0.55
    PreExecute
    -0.52
    ValueStyle
    -0.51
     AssemblyCulture
    -0.49
    RTHOOK
    -0.48
    WaitGroup
    -0.48
    IntoConstraints
    -0.46
    帖最后由
    -0.46
     OMITBAD
    -0.44
    POSITIVE LOGITS
    cửa
    0.51
     ElementRef
    0.49
    \{\\
    0.48
    Gön
    0.46
     للمعارف
    0.43
     ComVisible
    0.41
     FishBase
    0.40
     needles
    0.40
    roidery
    0.39
    TextBoxColumn
    0.39
    Activations Density 17.186%

    No Known Activations