© 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. 8563
    Prev
    Next
    INDEX
    Explanations

    phrases relating to legal procedures or standards

    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
     Мексичка
    -0.94
     isComment
    -0.83
    ConstraintMaker
    -0.82
    didSet
    -0.82
    duled
    -0.81
     Santander
    -0.78
     Merz
    -0.77
     Valenzuela
    -0.77
    ambilan
    -0.75
    diana
    -0.74
    POSITIVE LOGITS
     Forth
    1.21
     forth
    1.20
    Forth
    0.99
    forth
    0.83
    AndEndTag
    0.62
     carica
    0.62
     Forward
    0.61
    i
    0.61
     Forster
    0.60
    strong
    0.59
    Activations Density 0.008%

    No Known Activations