© 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. 5064
    Prev
    Next
    INDEX
    Explanations

    references to the percentage of data points or thresholds in data analysis

    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
    -------------</
    -0.77
    addCriterion
    -0.76
     فريبيس
    -0.76
     Reverso
    -0.74
     ExecuteAsync
    -0.69
    Попис
    -0.69
    LookAnd
    -0.68
    UseVisualStyle
    -0.68
     doInBackground
    -0.65
     kasarigan
    -0.64
    POSITIVE LOGITS
    utoff
    0.98
    cutoff
    0.64
     cutoff
    0.61
    mø
    0.57
    händler
    0.51
     sanitaires
    0.50
     contatto
    0.49
     déliv
    0.48
     Various
    0.48
     mostrarse
    0.47
    Activations Density 0.037%

    No Known Activations