© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12927
    Prev
    Next
    INDEX
    Explanations

    mentions of the Saints, particularly their name or references to them as a group

    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
    AutoScale
    -0.61
     EconPapers
    -0.58
     HasFactory
    -0.56
    rawtypes
    -0.56
    UnusedPrivate
    -0.56
     Otis
    -0.56
     Pollack
    -0.55
     esternos
    -0.54
     Barlow
    -0.53
     <<<<<<<<<<<<<<
    -0.53
    POSITIVE LOGITS
     Saints
    2.97
     saints
    2.88
    Saints
    2.41
     saint
    1.75
    aints
    1.35
    saint
    1.23
     SAINT
    0.91
     santos
    0.89
    Sain
    0.87
     Sain
    0.82
    Activations Density 0.001%

    No Known Activations