© 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. 28472
    Prev
    Next
    INDEX
    Explanations

    code syntax elements related to programming structures or concepts

    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
    AdapterView
    -0.55
    TimeUnit
    -0.45
    -
    -0.45
    <h2>
    -0.45
     ·
    -0.45
    <table>
    -0.44
    وند
    -0.44
    ní
    -0.43
    ApiOperation
    -0.43
    printStackTrace
    -0.43
    POSITIVE LOGITS
    <^
    1.26
     myſelf
    0.99
     bezeichneter
    0.94
     himſelf
    0.93
    oa̍t
    0.91
    يكب
    0.89
    IUrlHelper
    0.88
     Efq
    0.86
    saraba
    0.85
    EDEFAULT
    0.84
    Activations Density 0.001%

    No Known Activations