© 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. 23671
    Prev
    Next
    INDEX
    Explanations

    terms related to legal mail and prison correspondence

    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
    BuildContext
    -0.75
    ViewFeatures
    -0.73
    MeasureSpec
    -0.69
     StatefulWidget
    -0.68
    iczny
    -0.68
    EndContext
    -0.68
    RectangleBorder
    -0.68
     resourceCulture
    -0.68
     CreateTagHelper
    -0.66
     UnityEngine
    -0.66
    POSITIVE LOGITS
     MAIL
    1.16
     mail
    1.12
     Mail
    1.06
    MAIL
    0.95
     Postal
    0.94
    Mail
    0.92
     mailing
    0.91
     postal
    0.88
    mail
    0.87
    Postal
    0.87
    Activations Density 0.015%

    No Known Activations