© 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. 16688
    Prev
    Next
    INDEX
    Explanations

    terms related to legal roles and parties in court cases

    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
    ArgsConstructor
    -0.74
    queryInterface
    -0.69
     ujednoznacz
    -0.68
    esModule
    -0.59
    <bos>
    -0.57
    #
    -0.55
     convi
    -0.55
    достатки
    -0.54
    CascadeType
    -0.53
    Personensuche
    -0.53
    POSITIVE LOGITS
     privées
    0.66
    λισ
    0.58
    IVIDUAL
    0.58
     internetowa
    0.57
     virtuales
    0.57
     tâches
    0.57
    kozás
    0.55
     tomada
    0.54
     发表于
    0.54
     mourir
    0.53
    Activations Density 0.039%

    No Known Activations