© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15517
    Prev
    Next
    INDEX
    Explanations

    references to a foundational element or principle, specifically the concept of a "basis" used in various scientific and technical contexts

    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
    .*")]
    -0.98
     فريبيس
    -0.90
    ergies
    -0.87
     $_"
    -0.86
    aryen
    -0.85
    SharedDtor
    -0.83
     Majefty
    -0.83
     HttpNotFound
    -0.83
     myſelf
    -0.83
    tagHelperRunner
    -0.81
    POSITIVE LOGITS
     (
    0.58
    (
    0.49
    ,
    0.48
    List
    0.48
    one
    0.47
    :
    0.46
    <em>
    0.46
    g
    0.46
    ieważ
    0.45
    <eos>
    0.44
    Activations Density 0.002%

    No Known Activations