© 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. 14520
    Prev
    Next
    INDEX
    Explanations

    phrases related to distractions or red herrings in discussions or narratives

    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
     дописавши
    -0.72
    ArgumentParser
    -0.68
    IsContent
    -0.66
    ACGIH
    -0.63
    Przypisy
    -0.62
    withIdentifier
    -0.61
     resourceCulture
    -0.59
    MouseAdapter
    -0.58
     endforeach
    -0.56
     PropTypes
    -0.54
    POSITIVE LOGITS
    RegressionTest
    0.62
     focus
    0.57
     issues
    0.55
     betweenstory
    0.54
     issue
    0.53
     foremost
    0.53
    ISSUES
    0.53
    issues
    0.53
     focuses
    0.52
     trivial
    0.52
    Activations Density 0.198%

    No Known Activations