© 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. 18434
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to legal cases and parties involved in legal matters

    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
    ustris
    -0.60
    hapsody
    -0.58
    onViewCreated
    -0.58
     decorativos
    -0.56
     remarquer
    -0.56
     prédé
    -0.56
     fantasia
    -0.55
    itanie
    -0.54
     traités
    -0.54
     chronique
    -0.53
    POSITIVE LOGITS
     تضيفلها
    0.84
     BoxDecoration
    0.77
    KommentareTeilen
    0.68
    AnchorStyles
    0.67
     cherchés
    0.61
    webElementXpaths
    0.61
    OGND
    0.61
    IndentedString
    0.60
     Paglinawan
    0.60
    yntaxException
    0.60
    Activations Density 0.095%

    No Known Activations