© 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. 10276
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal rules or injunctions

    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
     sneezing
    -0.48
    licky
    -0.47
    noin
    -0.45
    วา
    -0.45
    eden
    -0.43
    __*/
    -0.43
    Crawl
    -0.42
    Yeet
    -0.41
     mimo
    -0.41
     curieux
    -0.41
    POSITIVE LOGITS
    IBOutlet
    0.83
     StatefulWidget
    0.80
    awtextra
    0.75
    principalColumn
    0.74
    borderFill
    0.74
    PyTuple
    0.74
     doInBackground
    0.72
    ViewChild
    0.71
     onAnimation
    0.71
    simpleType
    0.70
    Activations Density 0.012%

    No Known Activations