© 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. 1367
    Prev
    Next
    INDEX
    Explanations

    function return statements in code

    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
     '{@
    -0.63
     riguardo
    -0.62
     venons
    -0.62
     avoient
    -0.59
     Carlsbad
    -0.59
    Handlung
    -0.59
     romanos
    -0.59
     connaissent
    -0.58
     Soko
    -0.58
    حياتها
    -0.57
    POSITIVE LOGITS
    return
    1.57
     return
    1.17
     Return
    1.13
     RETURN
    1.05
     Returns
    1.04
     returns
    1.02
     مشين
    0.99
    Returns
    0.96
    RETURN
    0.95
    Return
    0.93
    Activations Density 0.232%

    No Known Activations