© 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. 377
    Prev
    Next
    INDEX
    Explanations

    references to the collection and analysis of data

    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
     variant
    -0.40
     Priester
    -0.40
     cucchia
    -0.40
    之一
    -0.38
     exception
    -0.38
    näm
    -0.37
    grine
    -0.36
    の一つ
    -0.36
    liferay
    -0.36
     igång
    -0.36
    POSITIVE LOGITS
     data
    1.01
     Data
    1.01
     newData
    0.94
    Data
    0.93
     DATA
    0.88
     information
    0.88
     getData
    0.85
     데이터
    0.85
    data
    0.82
    数据
    0.81
    Activations Density 4.940%

    No Known Activations