© 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. 25786
    Prev
    Next
    INDEX
    Explanations

    quantifiable measurements and technical 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
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.77
     myſelf
    -0.71
     ་་
    -0.71
     houſe
    -0.71
     Anſ
    -0.70
     Reſ
    -0.69
     Majefty
    -0.69
     Efq
    -0.69
     Diſ
    -0.68
     faſt
    -0.68
    POSITIVE LOGITS
    setVerticalGroup
    0.77
    URLException
    0.57
    AccessException
    0.54
     gainera
    0.53
     réessayer
    0.51
    тация
    0.48
     GetEnumerator
    0.48
    ollectionView
    0.48
    stopPropagation
    0.47
     unknownFields
    0.47
    Activations Density 0.581%

    No Known Activations