© 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. 14537
    Prev
    Next
    INDEX
    Explanations

    instances of the closing statement in programming or scripting languages

    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
    +#+#
    -0.97
     AppColors
    -0.89
     photolibrary
    -0.83
    "</
    -0.82
     groupId
    -0.80
     Colette
    -0.79
    ^(@)
    -0.78
     Volga
    -0.78
    "}
    -0.77
     Alsace
    -0.77
    POSITIVE LOGITS
     Fi
    1.15
     fi
    1.03
    Fi
    1.00
    fi
    0.99
    FI
    0.80
     FI
    0.75
     viewDidLoad
    0.72
     Fie
    0.68
    kron
    0.63
     фи
    0.63
    Activations Density 0.012%

    No Known Activations