© 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. 15865
    Prev
    Next
    INDEX
    Explanations

    phrases related to exchanges or trade-offs in discussions

    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
     للمعارف
    -0.82
     '\\;'
    -0.71
    ainville
    -0.71
    Tikang
    -0.68
    tuy
    -0.61
    oine
    -0.60
    TextHelper
    -0.60
    iastical
    -0.59
    eclared
    -0.57
    oys
    -0.57
    POSITIVE LOGITS
     recipro
    0.52
    交换
    0.50
     exchanged
    0.48
     exchange
    0.48
    InstanceState
    0.47
     reciprocal
    0.47
     Entry
    0.46
     REQU
    0.45
     Require
    0.45
     Requ
    0.45
    Activations Density 0.026%

    No Known Activations