Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 8295
    Prev
    Next
    INDEX
    Explanations

    references to the judicial system and legal terms related to United States courts

    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
    Personendaten
    -0.74
    newtheorem
    -0.53
    TypedValue
    -0.52
     šal
    -0.51
    Soporte
    -0.51
    šanās
    -0.51
    MessageState
    -0.50
    merie
    -0.50
    damento
    -0.47
    STATE
    -0.47
    POSITIVE LOGITS
     Commencez
    0.71
    !*\
    0.63
    beke
    0.62
    lgica
    0.61
    NCC
    0.59
    posedge
    0.59
    elernt
    0.56
     oprot
    0.56
    adpleegd
    0.55
    FormTagHelper
    0.54
    Activations Density 0.022%

    No Known Activations