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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8482
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to criminal offenses and judicial procedures

    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
    :✨
    -0.54
    دانشنامهٔ
    -0.50
     kasarigan
    -0.50
     Parenthood
    -0.47
    @@
    -0.47
    cheng
    -0.47
    pova
    -0.44
    Халык
    -0.43
    Elisa
    -0.42
     siglas
    -0.41
    POSITIVE LOGITS
    endphp
    0.82
     estekak
    0.77
     متعلقه
    0.66
    WebElementEntity
    0.65
     Réponses
    0.63
    reportWebVitals
    0.62
    queryInterface
    0.62
     CreateTagHelper
    0.61
    })()
    0.60
    جغرافيا
    0.59
    Activations Density 0.081%

    No Known Activations