© 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. 32137
    Prev
    Next
    INDEX
    Explanations

    declarations and definitions of function parameters in C++ 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
    <strong>
    -0.65
    me
    -0.65
    on
    -0.63
    Portail
    -0.59
    or
    -0.58
    l
    -0.58
    up
    -0.57
    2
    -0.54
    َ
    -0.54
    *
    -0.54
    POSITIVE LOGITS
     argc
    2.20
    argc
    1.76
    RunWith
    0.75
    numerusform
    0.75
    VersionUID
    0.74
     MainAxisSize
    0.74
     AssemblyTitle
    0.73
    ServletException
    0.72
    curacy
    0.71
     FormData
    0.70
    Activations Density 0.002%

    No Known Activations