Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 32528
    Prev
    Next
    INDEX
    Explanations

    elements indicative of structured data, such as forms or informational templates

    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
     polaroid
    -0.49
     ब्रेकडाउन
    -0.48
     broder
    -0.48
    HomeAsUpEnabled
    -0.45
    asmuch
    -0.45
     माल
    -0.44
     Tym
    -0.43
     manten
    -0.43
     Tana
    -0.43
     sidor
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.75
    تقاوى
    0.74
    matchCondition
    0.69
    complexContent
    0.69
     uska
    0.69
    ValueStyle
    0.66
    RegistryLite
    0.65
    RenderAtEndOf
    0.65
    المناصب
    0.63
    archiviato
    0.62
    Activations Density 0.155%

    No Known Activations