© 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. 2-RES-MATRYOSHKA-DC
    7. 6703
    Prev
    Next
    INDEX
    Explanations

    references to scarce or limited quantities

    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
    ...")
    -0.56
    untamente
    -0.55
     prostu
    -0.53
    voorbeeld
    -0.53
    ukah
    -0.52
    lably
    -0.51
     obstante
    -0.51
    etera
    -0.51
    ...');
    -0.50
    yep
    -0.50
    POSITIVE LOGITS
    Few
    1.70
     Few
    1.62
    few
    1.50
     few
    1.39
     FEW
    1.29
     rarely
    1.22
     seldom
    1.20
     Rarely
    1.08
     pocas
    1.05
     poucos
    0.98
    Activations Density 0.064%

    No Known Activations