© 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. 28602
    Prev
    Next
    INDEX
    Explanations

    elements related to demands and agreements in negotiation contexts

    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
    SharedCtor
    -0.67
    MessageTagHelper
    -0.61
    спонд
    -0.61
    winston
    -0.57
    ⓧ
    -0.56
    ագրություններ
    -0.54
    #![
    -0.54
    }`}
    -0.52
     MainAxisSize
    -0.52
     CascadeType
    -0.51
    POSITIVE LOGITS
     obeys
    0.66
     obey
    0.58
    tellt
    0.56
     demanded
    0.55
     comply
    0.54
     complied
    0.52
     conform
    0.52
     wajib
    0.50
    centralwidget
    0.50
     obblig
    0.50
    Activations Density 0.185%

    No Known Activations