© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19614
    Prev
    Next
    INDEX
    Explanations

    C++ programming constructs, including header file inclusions and using directives

    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
     متعلقه
    -0.93
     resourceCulture
    -0.87
    rungsseite
    -0.84
    はじめに
    -0.81
    曖昧さ回避
    -0.81
    afficheront
    -0.78
     disambiguazione
    -0.75
    BeginContext
    -0.69
    saraba
    -0.69
    homonymie
    -0.67
    POSITIVE LOGITS
     '\\;'
    0.51
    spesies
    0.43
    clud
    0.43
     speech
    0.43
    penuhi
    0.43
    ebilir
    0.42
    ắp
    0.40
    вла
    0.40
     diligen
    0.40
     Ven
    0.40
    Activations Density 0.019%

    No Known Activations