Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14428
    Prev
    Next
    INDEX
    Explanations

    references to plasma-related topics, particularly frequencies, parameters, and methods used in plasma physics and related experiments

    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
    -------------</
    -0.49
    𝑞
    -0.49
    stal
    -0.47
     اب
    -0.47
     pousse
    -0.47
     Doctor
    -0.45
     Mind
    -0.45
    assertAll
    -0.45
    tonsoft
    -0.44
     deix
    -0.44
    POSITIVE LOGITS
    Plas
    1.87
     Plas
    1.72
    plas
    1.26
    Datuak
    1.00
     Plastics
    0.96
    Plasmid
    0.93
    NonQuery
    0.88
     plastics
    0.75
    atis
    0.72
     cutter
    0.70
    Activations Density 0.003%

    No Known Activations