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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19202
    Prev
    Next
    INDEX
    Explanations

    terms related to the Ottoman Empire and its governance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.83
    AddTagHelper
    -0.82
    GEBURTSDATUM
    -0.81
    WaitGroup
    -0.81
     CreateTagHelper
    -0.80
    utilisons
    -0.79
    AndEndTag
    -0.78
     transfieras
    -0.77
    RegistryLite
    -0.77
    GraphicsUnit
    -0.75
    POSITIVE LOGITS
     empire
    0.56
     Empire
    0.54
     imperio
    0.50
     импе
    0.50
    打击
    0.48
    verwaltung
    0.46
     EMPIRE
    0.45
    empire
    0.45
    Internal
    0.44
     wewnętr
    0.44
    Activations Density 0.128%

    No Known Activations