© 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. 6926
    Prev
    Next
    INDEX
    Explanations

    instances of exceeding or surpassing a certain limit or threshold

    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
     ISNI
    -0.65
    theless
    -0.63
    skosten
    -0.60
     Kaufman
    -0.57
     vitamine
    -0.56
     Winaray
    -0.56
     Brasileira
    -0.55
     Hobson
    -0.54
     PAPERS
    -0.54
    ữa
    -0.54
    POSITIVE LOGITS
     exceed
    2.72
     exceeds
    2.38
     exceeded
    2.28
     exceeding
    2.25
     surpass
    1.42
     dépasse
    1.41
     превы
    1.37
     surpassing
    1.35
    ceed
    1.34
     surpassed
    1.31
    Activations Density 0.006%

    No Known Activations