© 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. 9134
    Prev
    Next
    INDEX
    Explanations

    references to legal cases or court designations

    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
    AddTagHelper
    -0.53
     her
    -0.50
    parsedMessage
    -0.50
    </i>
    -0.49
    ni
    -0.48
    o
    -0.48
    ू
    -0.46
    </b>
    -0.46
    os
    -0.46
     ví
    -0.45
    POSITIVE LOGITS
     للمعارف
    1.06
     itſelf
    1.02
    ſelves
    0.96
     Majefty
    0.96
     houſe
    0.93
     pinulongan
    0.90
     Efq
    0.88
     Савезне
    0.87
     myſelf
    0.87
     ExecuteAsync
    0.86
    Activations Density 0.011%

    No Known Activations