© 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. 2054
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages and code-related elements

    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
     Supremo
    -0.73
     Oeste
    -0.72
     Mitar
    -0.71
     Italij
    -0.71
     himſelf
    -0.69
     Jefus
    -0.68
     schi
    -0.67
    ücks
    -0.66
     fubject
    -0.66
     Certo
    -0.65
    POSITIVE LOGITS
     languages
    1.59
     Language
    1.48
    Languages
    1.48
     Languages
    1.47
    languages
    1.42
     language
    1.41
    Language
    1.34
     LANGUAGE
    1.27
     Lang
    1.25
    language
    1.24
    Activations Density 0.065%

    No Known Activations