© 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. 22-RES-MATRYOSHKA-DC
    7. 1540
    Prev
    Next
    INDEX
    Explanations

    mentions of rules, laws, and standards, in a legal or ethical context

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    abestanden
    -0.75
    PostExecute
    -0.69
    UseVisualStyle
    -0.68
    новниш
    -0.68
    tagHelperRunner
    -0.63
    enumi
    -0.62
     Betracht
    -0.58
    SerializedSize
    -0.57
     ostavi
    -0.56
    MockBean
    -0.55
    POSITIVE LOGITS
     rules
    1.95
     guidelines
    1.73
    rules
    1.57
     standards
    1.55
     regulations
    1.51
     Rules
    1.48
    Rules
    1.45
     norms
    1.41
    guidelines
    1.39
     rule
    1.33
    Activations Density 2.072%

    No Known Activations