© 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. 13569
    Prev
    Next
    INDEX
    Explanations

    references to diffraction or diffraction data

    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
     فريبيس
    -0.57
     privés
    -0.56
     giù
    -0.56
     tombé
    -0.54
     tache
    -0.53
    utnant
    -0.52
     caught
    -0.52
     prywat
    -0.51
     Swal
    -0.51
    Scroll
    -0.50
    POSITIVE LOGITS
    uber
    1.70
    ubert
    1.20
     diffraction
    1.07
    UBER
    0.98
     tuber
    0.85
     Diffraction
    0.85
     للاسماء
    0.85
    tuber
    0.84
    出版年
    0.77
     Tuber
    0.76
    Activations Density 0.008%

    No Known Activations