© 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. 2-RES-MATRYOSHKA-DC
    7. 5272
    Prev
    Next
    INDEX
    Explanations

    key identifiers or labels related to categories or classifications

    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
     Lana
    -0.82
     Topeka
    -0.78
     Audiodateien
    -0.77
    Lana
    -0.76
    Aves
    -0.74
     norman
    -0.73
    esgue
    -0.73
     Norm
    -0.72
    !*\
    -0.70
     Ophelia
    -0.70
    POSITIVE LOGITS
     дописавши
    0.80
     Vander
    0.77
     Simons
    0.73
     Hok
    0.69
     Anton
    0.66
     ANTON
    0.65
     hok
    0.64
     trajets
    0.63
     maravillas
    0.63
     Stanton
    0.63
    Activations Density 1.574%

    No Known Activations