© 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. 2-RES-MATRYOSHKA-DC
    7. 7495
    Prev
    Next
    INDEX
    Explanations

    references or mentions of a specific person named Martin

    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
    Negative Logits
    igshid
    -0.82
    NOPQRST
    -0.77
    RenderAtEndOf
    -0.69
    herin
    -0.69
    
    -0.67
    Примечания
    -0.66
    adaptiveStyles
    -0.66
    Jared
    -0.65
    Highway
    -0.65
     Hathaway
    -0.64
    POSITIVE LOGITS
     Martin
    3.55
    Martin
    3.34
     MARTIN
    2.98
     martin
    2.81
    MARTIN
    2.52
    martin
    2.39
     Martín
    2.16
     Martins
    2.02
    Martín
    1.66
     mart
    1.52
    Activations Density 0.007%

    No Known Activations