© 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. 2326
    Prev
    Next
    INDEX
    Explanations

    the word 'batch' and the file extension '.bat'

    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
     Nesse
    -0.77
    complexContent
    -0.72
    脚注の使い方
    -0.68
    Uli
    -0.67
     Heid
    -0.66
    SeekBar
    -0.63
     Bist
    -0.61
     MenuView
    -0.61
     Leona
    -0.60
     leetcode
    -0.60
    POSITIVE LOGITS
     batch
    3.05
     Batch
    2.84
    batch
    2.83
    Batch
    2.78
     BATCH
    2.67
    BATCH
    2.59
     batches
    2.38
    batches
    1.95
    批
    1.59
     lote
    1.55
    Activations Density 0.010%

    No Known Activations