© 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. 134
    Prev
    Next
    INDEX
    Explanations

    references to specific items or topics in a given 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
    LookAnd
    -0.86
    msgTypes
    -0.56
     Jue
    -0.52
    hup
    -0.52
    GEBURTSDATUM
    -0.52
    adl
    -0.51
    legion
    -0.49
    legal
    -0.49
    ◆◇
    -0.49
     ſever
    -0.48
    POSITIVE LOGITS
     this
    1.15
     This
    1.04
    This
    1.03
     THIS
    1.03
     questa
    0.90
    this
    0.90
     these
    0.90
    Этот
    0.90
     dieser
    0.88
     Dieses
    0.88
    Activations Density 1.093%

    No Known Activations