© 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. 5303
    Prev
    Next
    INDEX
    Explanations

    instances where the word "distinguish" or related forms appear

    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
     ویکی‌پدی
    -0.71
     beginnetje
    -0.71
     Cauchy
    -0.68
     upheaval
    -0.67
    XmlAccessorType
    -0.66
    severance
    -0.66
    اسف
    -0.65
    -------------</
    -0.64
    DotNetBar
    -0.64
    impinan
    -0.62
    POSITIVE LOGITS
     distinguish
    2.41
     distinguishing
    2.14
     distinguished
    2.13
     distinguishes
    2.09
     distinction
    2.02
    distingu
    2.02
     distingu
    1.84
    dist
    1.83
     disting
    1.82
     distinguir
    1.77
    Activations Density 0.145%

    No Known Activations