© 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-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1523
    Prev
    Next
    INDEX
    Explanations

    the word 'national' and associated concepts like news agencies or bodies

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     lune
    -0.54
    bree
    -0.54
    ρει
    -0.54
    wifery
    -0.54
    MathML
    -0.53
     Proxy
    -0.53
    ebi
    -0.53
     Eylül
    -0.52
    ness
    -0.52
    Proxy
    -0.52
    POSITIVE LOGITS
    NATIONAL
    1.76
     national
    1.74
    national
    1.73
    National
    1.66
     National
    1.66
     NATIONAL
    1.64
     nationaux
    1.45
     nationale
    1.44
     nationals
    1.44
     nacionais
    1.40
    Activations Density 0.273%

    No Known Activations