© 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. 12-RES-MATRYOSHKA-DC
    7. 6348
    Prev
    Next
    INDEX
    Explanations

    references to knowledge and intent in legal contexts, particularly relating to liability and negligence

    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
    AccessorTable
    -0.68
    rawDesc
    -0.66
    subpackage
    -0.59
    Portail
    -0.57
     intptr
    -0.57
     transfieras
    -0.55
    LLocation
    -0.55
     typelib
    -0.54
    engeti
    -0.54
    ivir
    -0.53
    POSITIVE LOGITS
    出版年
    0.57
     aware
    0.52
    Aware
    0.50
    knew
    0.50
     knowing
    0.49
    aware
    0.49
     Aware
    0.48
    conscious
    0.47
    knowing
    0.46
     knew
    0.45
    Activations Density 0.343%

    No Known Activations