© 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. 0-RES-MATRYOSHKA-DC
    7. 10738
    Prev
    Next
    INDEX
    Explanations

    references to a specific proper noun, likely a person's name

    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
     Mo
    -1.82
    Mo
    -1.53
    bootstrapcdn
    -0.82
     calendriers
    -0.70
    AsUp
    -0.68
    adaptiveStyles
    -0.68
     Mov
    -0.63
    THISDAY
    -0.62
    ially
    -0.60
    MessageTagHelper
    -0.60
    POSITIVE LOGITS
    mo
    0.68
    mos
    0.66
    tagHelperRunner
    0.65
    MO
    0.63
    mor
    0.62
    mod
    0.56
     mor
    0.56
    Portail
    0.53
    mode
    0.51
     Consultado
    0.51
    Activations Density 0.003%

    No Known Activations