© 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. 29511
    Prev
    Next
    INDEX
    Explanations

    function calls and elements being manipulated or placed in programming contexts

    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
    PyErr
    -0.68
    ArgsConstructor
    -0.58
    TagMode
    -0.56
    nup
    -0.53
    щ
    -0.50
    LookAndFeel
    -0.50
    
    -0.49
    labelledby
    -0.49
     disambiguazione
    -0.49
     geslacht
    -0.49
    POSITIVE LOGITS
    WriteTagHelper
    0.68
     new
    0.65
     addNew
    0.58
     newcomer
    0.55
    )++;
    0.55
     nouveaux
    0.55
     createNew
    0.54
     الجديدة
    0.53
    )$_
    0.53
    ToAdd
    0.53
    Activations Density 0.069%

    No Known Activations