© 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. 6586
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to approval processes and authorization

    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
     shift
    -0.60
     
    -0.58
    เค
    -0.57
    ya
    -0.56
    ing
    -0.55
    be
    -0.53
    &
    -0.52
    en
    -0.52
     &
    -0.51
     H
    -0.51
    POSITIVE LOGITS
     Approval
    1.49
     approvals
    1.43
     approval
    1.38
     approve
    1.34
     approving
    1.31
     approves
    1.30
    approval
    1.29
     APPROVAL
    1.28
    Approval
    1.27
     disapproval
    1.19
    Activations Density 0.031%

    No Known Activations