© 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. 23507
    Prev
    Next
    INDEX
    Explanations

    terms related to configuration and programming structures in software development

    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
     незавершена
    -0.66
    AnimationsModule
    -0.65
    msgTypes
    -0.61
     Ause
    -0.56
    اديم
    -0.55
    uver
    -0.54
     uintptr
    -0.53
    انيف
    -0.52
     Италијани
    -0.51
    flink
    -0.50
    POSITIVE LOGITS
    +#+#
    0.62
     Chwiliwch
    0.61
    Revenir
    0.54
    when
    0.53
    在于
    0.52
     quando
    0.51
     when
    0.51
    ิจ
    0.51
    quando
    0.51
    WHEN
    0.50
    Activations Density 0.073%

    No Known Activations