© 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. 10161
    Prev
    Next
    INDEX
    Explanations

    references to keys in a data format, likely related to data structures or programming

    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
    AddTagHelper
    -0.57
     tri
    -0.53
    ena
    -0.52
    ések
    -0.51
     un
    -0.50
    uan
    -0.50
     sequelize
    -0.49
    tierten
    -0.49
    matian
    -0.48
     
    -0.48
    POSITIVE LOGITS
    存于互联网档案馆
    0.92
     itſelf
    0.71
     Houſe
    0.69
    abestanden
    0.67
    featureID
    0.67
    istoitu
    0.65
     pleaſure
    0.64
    InjectAttribute
    0.63
     تانيه
    0.63
     houſe
    0.63
    Activations Density 0.001%

    No Known Activations