© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15919
    Prev
    Next
    INDEX
    Explanations

    references to specific specialized transformation devices or tools used by characters, often with detailed naming

    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
    mybatisplus
    -0.51
     سبيل
    -0.51
    inverno
    -0.49
    ecture
    -0.48
     européen
    -0.48
    GraphicsUnit
    -0.47
     Each
    -0.47
     satisfait
    -0.46
    zhu
    -0.46
     ciasc
    -0.46
    POSITIVE LOGITS
    omi
    3.06
    OMI
    1.98
    omia
    0.94
    imi
    0.74
    EDEFAULT
    0.74
    emi
    0.69
    omie
    0.69
    RenderAtEndOf
    0.69
    omis
    0.65
    omy
    0.63
    Activations Density 0.003%

    No Known Activations