© 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. 23589
    Prev
    Next
    INDEX
    Explanations

    HTML tags and syntax

    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
    <eos>
    -0.59
    ↵↵
    -0.59
    ']){
    -0.51
     vele
    -0.51
    ']):
    -0.51
    ↵↵↵↵↵↵↵
    -0.49
    ↵↵↵
    -0.48
    ↵
    -0.48
    <bos>
    -0.46
    ])):
    -0.46
    POSITIVE LOGITS
    Samedi
    0.75
     reaſon
    0.72
     reafon
    0.71
    +#+#
    0.71
     referenties
    0.68
    Tikang
    0.68
     Mudd
    0.66
     HasFactory
    0.66
     ArrayAdapter
    0.66
    ppincott
    0.66
    Activations Density 0.012%

    No Known Activations