© 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. 315
    Prev
    Next
    INDEX
    Explanations

    legal arguments and assertions made 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
    IUrlHelper
    -0.67
    AndEndTag
    -0.66
     CURIAM
    -0.62
    BASEPATH
    -0.61
     SafeMath
    -0.60
     userSchema
    -0.60
     '\\;'
    -0.57
    Tembelea
    -0.57
     RouterModule
    -0.56
     newBuilder
    -0.56
    POSITIVE LOGITS
     argued
    0.69
     argues
    0.67
     argumenta
    0.63
     argue
    0.60
     submitted
    0.59
     submits
    0.59
    主張
    0.58
     argument
    0.58
     contends
    0.58
     alleges
    0.57
    Activations Density 1.745%

    No Known Activations