© 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. 0-RES-MATRYOSHKA-DC
    7. 12800
    Prev
    Next
    INDEX
    Explanations

    mentions of processor counts or the concept of processing units

    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
     cancel
    -0.66
    cancel
    -0.64
     hefyd
    -0.57
    cpu
    -0.56
     cancellations
    -0.56
    makeConstraints
    -0.54
    鰭
    -0.53
     Cancel
    -0.53
    quiti
    -0.52
    unfinished
    -0.51
    POSITIVE LOGITS
    processor
    2.73
    processors
    2.06
    Processor
    1.52
     processor
    1.18
     Processor
    1.12
    Processors
    1.09
    处理器
    0.93
     processors
    0.77
     Processors
    0.67
     procesador
    0.65
    Activations Density 0.007%

    No Known Activations