© 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. 30940
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and attributes used in software assemblies

    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
     K
    -0.52
    bles
    -0.50
     un
    -0.49
    rom
    -0.48
    urs
    -0.47
    сь
    -0.45
    fo
    -0.45
    igne
    -0.45
    …
    -0.44
    men
    -0.44
    POSITIVE LOGITS
    ByVersion
    3.56
     ProtoMessage
    3.39
    AddTagHelper
    2.14
     EconPapers
    1.80
     resourceCulture
    1.73
    Personensuche
    1.73
    ValueStyle
    1.71
     AssemblyCulture
    1.70
    ThroughAttribute
    1.69
     ExecuteAsync
    1.69
    Activations Density 0.005%

    No Known Activations