© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24068
    Prev
    Next
    INDEX
    Explanations

    terms related to tax regulations and legal requirements for trusts

    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
    Negative Logits
    ArgsConstructor
    -0.91
    PreferredItem
    -0.81
     الحره
    -0.77
     ExecuteAsync
    -0.76
    __":
    -0.76
    __':
    -0.75
    Parcelize
    -0.74
    WindowConstants
    -0.73
     InputDecoration
    -0.72
    awtextra
    -0.71
    POSITIVE LOGITS
     seemingly
    0.53
    praw
    0.49
     arguably
    0.45
    lasyon
    0.44
    relatively
    0.43
     Parece
    0.43
    Navig
    0.42
     juris
    0.42
     seems
    0.42
     recently
    0.42
    Activations Density 0.210%

    No Known Activations