© 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. 17068
    Prev
    Next
    INDEX
    Explanations

    references to web or API structures and specifications

    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
     
    -0.67
     "
    -0.65
     ST
    -0.62
     M
    -0.60
     '
    -0.56
    -
    -0.56
     (
    -0.56
     or
    -0.53
     St
    -0.52
     s
    -0.51
    POSITIVE LOGITS
     itſelf
    1.16
     pleaſure
    1.15
    ſelves
    1.01
     ſtate
    0.99
     незавершена
    0.99
     auffi
    0.96
     myſelf
    0.95
     nakalista
    0.95
     purpoſe
    0.92
     houſe
    0.92
    Activations Density 0.001%

    No Known Activations