© 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. 19360
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases regarding evidence and court proceedings

    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
    QMetaType
    -0.86
     виправивши
    -0.85
     kaarangay
    -0.82
     ویکی‌پدیای
    -0.82
     ffilmiau
    -0.73
    asteroide
    -0.72
    UnusedPrivate
    -0.72
    AndEndTag
    -0.69
     وتسجيلات
    -0.68
     mergeFrom
    -0.67
    POSITIVE LOGITS
     disponibilités
    0.57
    mbal
    0.46
     ujednoznacz
    0.45
    mountable
    0.45
     ä
    0.45
    mbing
    0.42
    useState
    0.42
     TAMBIÉN
    0.41
     types
    0.41
     ти
    0.40
    Activations Density 0.072%

    No Known Activations