© 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. 13962
    Prev
    Next
    INDEX
    Explanations

    formal programming syntax elements, specifically those related to function and pointer declarations

    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
     يتيمه
    -0.69
    KommentareTeilen
    -0.66
    Transkript
    -0.65
    expandindo
    -0.63
     виправивши
    -0.61
    IUrlHelper
    -0.60
     Montagu
    -0.59
    Демографія
    -0.57
     magasiner
    -0.56
     octaves
    -0.55
    POSITIVE LOGITS
    awakeFromNib
    0.58
    culin
    0.55
    CloseOperation
    0.51
    neus
    0.50
     ""],
    0.49
    ulon
    0.48
    ".$_
    0.48
    RectangleBorder
    0.48
    })).
    0.48
    medriver
    0.47
    Activations Density 0.000%

    No Known Activations