© 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. 28603
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation in equations

    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
     Dey
    -0.52
     Che
    -0.50
     che
    -0.48
     himo
    -0.48
    kfree
    -0.47
     Att
    -0.47
    ah
    -0.46
    sema
    -0.46
     Al
    -0.45
    Deuter
    -0.45
    POSITIVE LOGITS
    SpringRunner
    0.81
    IMPORTED
    0.73
    PYX
    0.73
    picasso
    0.72
    ArgumentParser
    0.70
    onomía
    0.69
    AsStream
    0.69
     Administrativna
    0.68
     screwdriver
    0.67
     Agamemnon
    0.67
    Activations Density 0.009%

    No Known Activations