© 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. 30724
    Prev
    Next
    INDEX
    Explanations

    references to legal entities, claims, and responsibilities in a legal context

    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
    iotensin
    -0.44
     his
    -0.44
     immédi
    -0.42
    适
    -0.42
    op
    -0.41
     k
    -0.40
    Биография
    -0.40
     K
    -0.40
    Discography
    -0.40
    OP
    -0.39
    POSITIVE LOGITS
     itſelf
    0.93
     Jefus
    0.93
     Theſe
    0.92
     Diſ
    0.91
    ſelves
    0.90
    ſelf
    0.90
     Reſ
    0.90
     Offisielt
    0.89
     Monfieur
    0.89
     raiſ
    0.85
    Activations Density 0.054%

    No Known Activations