© 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. 19388
    Prev
    Next
    INDEX
    Explanations

    phrases relating to legal and structural specifics

    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
     &___
    -0.73
    setViewportView
    -0.62
    iastes
    -0.60
    AsUp
    -0.59
     كومونز
    -0.59
     sạn
    -0.59
    Rhestr
    -0.57
     يتيمه
    -0.56
     ويكيپيديا
    -0.56
     russes
    -0.56
    POSITIVE LOGITS
     Seeder
    0.52
     but
    0.49
    XPath
    0.49
    なくても
    0.44
    ells
    0.44
     concreto
    0.43
     dodge
    0.43
    かもしれませんが
    0.43
     MethodInfo
    0.43
     Sons
    0.43
    Activations Density 0.270%

    No Known Activations