© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15333
    Prev
    Next
    INDEX
    Explanations

    references to scientific 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
    usehen
    -0.43
     Photocase
    -0.43
     चीज़ों
    -0.42
    atguigu
    -0.40
    MemoryWarning
    -0.40
    φορά
    -0.39
    elif
    -0.38
    ollection
    -0.38
    edon
    -0.37
     للمعارف
    -0.36
    POSITIVE LOGITS
    NewUrlParser
    0.68
     ViewPager
    0.67
    xFFFFFF
    0.67
    __':
    0.64
     AssemblyCompany
    0.63
    breos
    0.63
     sociologist
    0.63
    <!--[
    0.63
    PageFactory
    0.62
    setVerticalGroup
    0.61
    Activations Density 0.125%

    No Known Activations