© 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. 297
    Prev
    Next
    INDEX
    Explanations

    terms and expressions related to definitions and naming conventions

    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
     too
    -0.36
     mukana
    -0.36
     Urteil
    -0.35
     demasi
    -0.35
    initComponents
    -0.34
     seems
    -0.34
     demasiado
    -0.34
     estuvo
    -0.34
     policías
    -0.33
     kemarin
    -0.33
    POSITIVE LOGITS
    Personendaten
    1.07
     called
    0.87
    called
    0.87
     CALLED
    0.83
    VersionUID
    0.81
     name
    0.77
     named
    0.77
     termed
    0.76
     AssemblyTitle
    0.76
     Called
    0.75
    Activations Density 2.837%

    No Known Activations