© 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. 21620
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court procedures and judgments

    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
    UpdateCommand
    -0.50
    ariate
    -0.50
    attery
    -0.45
    voyer
    -0.45
     sella
    -0.45
     Shel
    -0.44
     Verd
    -0.44
    ضور
    -0.44
     =~
    -0.43
     casque
    -0.43
    POSITIVE LOGITS
    SharedDtor
    0.91
    DockStyle
    0.82
     initComponents
    0.80
     jspb
    0.74
    ThroughAttribute
    0.67
    oa̍t
    0.65
    TagMode
    0.64
    writeFieldEnd
    0.64
    EndInit
    0.63
    setVerticalGroup
    0.61
    Activations Density 0.765%

    No Known Activations