© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11095
    Prev
    Next
    INDEX
    Explanations

    words related to the Arabic expressions of "present" or "exists" with specific references to certain entities

    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
    منون
    -0.68
    قيقي
    -0.63
    طبيق
    -0.54
    يران
    -0.54
    श्लेषण
    -0.54
    اشتم
    -0.54
    عاون
    -0.52
    ياه
    -0.51
    يادة
    -0.50
    فسير
    -0.50
    POSITIVE LOGITS
    ال
    1.27
    ب
    1.13
    أ
    1.10
    الأ
    1.09
    م
    1.03
    د
    0.99
    الم
    0.96
    ل
    0.96
    إ
    0.93
    ف
    0.93
    Activations Density 0.009%

    No Known Activations