© 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. 6240
    Prev
    Next
    INDEX
    Explanations

    numeric data and identifiers associated with components in code structures

    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
    mybatisplus
    -1.15
     itſelf
    -1.15
     незавершена
    -1.04
     lenker
    -1.03
     himſelf
    -1.02
     Majefty
    -1.02
     auroit
    -1.02
     myſelf
    -1.02
     Wikimedijinoj
    -0.98
     feroit
    -0.98
    POSITIVE LOGITS
    2
    0.94
    <eos>
    0.90
    1
    0.84
    3
    0.77
    4
    0.75
    ↵↵
    0.74
     
    0.74
    5
    0.71
    0
    0.70
    8
    0.66
    Activations Density 0.004%

    No Known Activations