© 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. 32558
    Prev
    Next
    INDEX
    Explanations

    variables and parameters in mathematical expressions

    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
    Negative Logits
    ro
    -0.75
    er
    -0.74
    ge
    -0.74
    ly
    -0.68
    u
    -0.66
    in
    -0.64
    I
    -0.62
    ar
    -0.61
    y
    -0.61
    l
    -0.61
    POSITIVE LOGITS
    abetes
    1.00
    izophrenia
    0.99
    endphp
    0.94
    lihood
    0.92
     aeruginosa
    0.92
    bootstrapcdn
    0.92
    Искәрмәләр
    0.91
    
    0.91
    rachtet
    0.88
    mobileqq
    0.88
    Activations Density 0.123%

    No Known Activations