© 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. 25057
    Prev
    Next
    INDEX
    Explanations

    references to technology-related discussions, particularly around issues and troubleshooting in software

    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
    leap
    -0.53
    wnie
    -0.52
    ætter
    -0.48
     corresponde
    -0.46
    Camp
    -0.45
     τὸν
    -0.44
     campana
    -0.44
    ându
    -0.44
     thereafter
    -0.44
     reda
    -0.43
    POSITIVE LOGITS
    }{*}{}
    0.77
    CppMethod
    0.71
    buttonBar
    0.70
    IsContent
    0.68
    theless
    0.65
    transQ
    0.65
    HtmlAttribute
    0.64
    invokeLater
    0.64
    tinyos
    0.62
    soever
    0.62
    Activations Density 0.005%

    No Known Activations