© 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. 8211
    Prev
    Next
    INDEX
    Explanations

    details about dates and times related to events

    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
     CURLOPT
    -0.54
    +#+#
    -0.49
    Diweddarwch
    -0.48
    日閲覧
    -0.47
    mony
    -0.46
     added
    -0.43
    ujen
    -0.43
     finished
    -0.43
     albero
    -0.43
     pronon
    -0.42
    POSITIVE LOGITS
    URLException
    0.70
     '\\;'
    0.68
    Kariera
    0.63
    DispatchToProps
    0.62
    ApiModel
    0.59
    ValueGenerated
    0.56
    stretch
    0.56
    invokeLater
    0.56
     stretch
    0.55
     Mediat
    0.55
    Activations Density 0.088%

    No Known Activations