© 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. 11359
    Prev
    Next
    INDEX
    Explanations

    references to scientific literature and citations

    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
     HttpNotFound
    -0.73
    TextAppearance
    -0.69
    numberOfLines
    -0.60
    المشاركات
    -0.53
    setValues
    -0.51
     Massen
    -0.50
    setViewportView
    -0.49
    LEADING
    -0.49
     Taken
    -0.48
     fone
    -0.48
    POSITIVE LOGITS
    RenderAtEndOf
    0.90
    homonymie
    0.80
    hoeddwyd
    0.68
    RegressionTest
    0.66
     يتيمه
    0.65
    oredCriteria
    0.63
     دیکھیے
    0.62
    pool
    0.59
     ویکی‌پدی
    0.59
     POOL
    0.59
    Activations Density 0.023%

    No Known Activations