© 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. 31846
    Prev
    Next
    INDEX
    Explanations

    references to specific programming help forums or Q&A platforms, particularly related to coding topics

    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
     Bakar
    -0.65
    yfikacja
    -0.63
    xase
    -0.62
    Nội
    -0.59
    DataPropertyName
    -0.59
    unen
    -0.58
     متعلقه
    -0.58
    Vidite
    -0.58
     Mondial
    -0.58
     rhestr
    -0.57
    POSITIVE LOGITS
    stackoverflow
    1.37
     Stack
    0.68
     Overflow
    0.68
     tartalomajánló
    0.59
     Exactos
    0.57
    ElementException
    0.57
    acke
    0.56
    overflow
    0.53
    trab
    0.52
    ArgsConstructor
    0.51
    Activations Density 0.003%

    No Known Activations