© 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. 8805
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to mathematical operations and their outcomes

    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
    NewUrlParser
    -0.74
    UserScript
    -0.73
    ieteur
    -0.66
    dafx
    -0.64
    \{\\
    -0.64
    DialogContent
    -0.61
     noDo
    -0.60
     Wicidata
    -0.60
    IndentedString
    -0.59
    
    -0.59
    POSITIVE LOGITS
     rum
    0.48
     }{@
    0.45
     diffus
    0.45
    归
    0.44
    documentclass
    0.43
    ppia
    0.43
     thrown
    0.43
     leases
    0.43
     boîtier
    0.43
     throws
    0.43
    Activations Density 0.006%

    No Known Activations