© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12137
    Prev
    Next
    INDEX
    Explanations

    references to diplomatic envoys or representatives

    oai_token-act-pair · gpt-4.1-nano
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.77
     HasFactory
    -0.73
    writeField
    -0.72
     فريبيس
    -0.69
     correctes
    -0.69
     InputDecoration
    -0.69
    yargs
    -0.69
    inguém
    -0.67
    writeFieldEnd
    -0.66
     ControllerBase
    -0.66
    POSITIVE LOGITS
     ambassador
    3.31
     Ambassador
    3.25
    Ambassador
    2.78
     ambassadors
    2.67
     Ambassadors
    2.39
     embaj
    2.00
     ambass
    1.86
     ambassade
    1.83
     Embaj
    1.52
     embassy
    1.51
    Activations Density 0.002%

    No Known Activations