© 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. 15956
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to definitions and variable declarations

    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
    IsContent
    -0.67
    Diwedd
    -0.65
    ValueStyle
    -0.55
     Wicidata
    -0.53
    EndContext
    -0.52
    AndEndTag
    -0.47
     But
    -0.46
    teness
    -0.46
    HtmlAttribute
    -0.46
    GRANTED
    -0.44
    POSITIVE LOGITS
    Rüyada
    0.85
     photolibrary
    0.68
    OOTDTY
    0.68
     Theſe
    0.68
    eseorang
    0.65
    PutMapping
    0.64
     zubehör
    0.63
     Anſ
    0.62
    Попис
    0.62
    DeleteMapping
    0.62
    Activations Density 0.518%

    No Known Activations