© 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. 32273
    Prev
    Next
    INDEX
    Explanations

    template definitions and type declarations used in programming, particularly in C++

    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
    脚注の使い方
    -0.69
    WriteBarrier
    -0.66
    tagHelperRunner
    -0.64
    Πηγές
    -0.63
    सन्दर्भ
    -0.61
    曖昧さ回避
    -0.60
    ValueGenerated
    -0.59
    ensement
    -0.59
    Diwedd
    -0.57
     tartalomajánló
    -0.57
    POSITIVE LOGITS
    AnchorStyles
    0.77
     ویکی‌پدیای
    0.54
     />);
    0.52
    iants
    0.51
     Normdatei
    0.50
     Besonders
    0.50
    </h2>
    0.47
    wall
    0.47
    ыгана
    0.47
     Danish
    0.47
    Activations Density 0.007%

    No Known Activations