© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1278
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and structures, particularly in programming contexts involving device or memory management

    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
    __':
    -0.79
    دانشنامهٔ
    -0.74
    ViewImports
    -0.70
     ویکی‌آمباردا
    -0.66
    躇
    -0.64
     Вікі
    -0.63
    Glej
    -0.63
    مصادر
    -0.61
    Datuak
    -0.59
    EDEFAULT
    -0.59
    POSITIVE LOGITS
    ('/:
    0.52
    opardy
    0.47
    ECONOM
    0.47
     localObject
    0.45
    EFIAPI
    0.43
    ranslated
    0.43
    tomcat
    0.43
     halos
    0.43
     anisotropy
    0.43
     phép
    0.42
    Activations Density 0.140%

    No Known Activations