© 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. 6345
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical data or coding information

    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
     avoient
    -0.91
     auroit
    -0.85
     zelve
    -0.85
     ainfi
    -0.84
     houſe
    -0.80
     auffi
    -0.80
     myſelf
    -0.80
     Jefus
    -0.78
     purpoſe
    -0.78
     juſ
    -0.77
    POSITIVE LOGITS
     lu
    0.49
     l
    0.48
     cla
    0.47
     ben
    0.47
     gi
    0.47
     le
    0.45
     di
    0.45
     it
    0.45
     fig
    0.45
    sche
    0.45
    Activations Density 0.174%

    No Known Activations