© 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. 3-RES-MATRYOSHKA-DC
    7. 1802
    Prev
    Next
    INDEX
    Explanations

    instances of the word "limit" or its variants and the articles "the" or "by" that commonly follow.

    oai_token-act-pair · gemini-2.0-flash
    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
     jLabel
    -0.66
    Dequeue
    -0.65
     Osama
    -0.64
     ModelExpression
    -0.59
    Jessie
    -0.58
    DispatchToProps
    -0.57
    ViewFeatures
    -0.57
    ージェ
    -0.56
    gın
    -0.55
    ített
    -0.55
    POSITIVE LOGITS
     limit
    2.84
     limits
    2.80
     limitation
    2.77
    limit
    2.70
     limitations
    2.70
     Limit
    2.70
     limited
    2.61
    Limit
    2.52
     Limits
    2.52
     LIMIT
    2.48
    Activations Density 0.416%

    No Known Activations