© 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. 28549
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data types in a codebase

    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
    parsedMessage
    -0.88
     resourceCulture
    -0.79
     للاسماء
    -0.75
     disambiguazione
    -0.74
    AccessorTable
    -0.73
    rungsseite
    -0.66
     CreateTagHelper
    -0.66
    verwijspagina
    -0.66
    sizeCache
    -0.63
    Personensuche
    -0.60
    POSITIVE LOGITS
     فريبيس
    0.70
    ֶה
    0.54
     NDEBUG
    0.53
     `;
    0.53
     CGRectMake
    0.52
     csrf
    0.51
     RestTemplate
    0.49
    JvmStatic
    0.48
     conda
    0.46
     cuticle
    0.46
    Activations Density 0.437%

    No Known Activations