© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3618
    Prev
    Next
    INDEX
    Explanations

    code structures related to class and function definitions in programming

    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
     disambiguazione
    -0.64
    ArrowToggle
    -0.60
     NSCoder
    -0.58
    AndEndTag
    -0.57
    ReusableCell
    -0.57
     JpaRepository
    -0.56
     يتيمه
    -0.55
    Portale
    -0.54
    ToAction
    -0.54
    IActionResult
    -0.54
    POSITIVE LOGITS
     مشين
    0.57
    livejournal
    0.57
    Билгалдахарш
    0.56
    ographique
    0.55
    "]));
    0.54
    åde
    0.52
    zugehen
    0.52
    eronau
    0.52
    Grüße
    0.50
     ailleurs
    0.50
    Activations Density 0.110%

    No Known Activations