© 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. 12144
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration and related emotional states

    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
     Biv
    -0.69
     financières
    -0.68
    Cod
    -0.66
    izier
    -0.66
     văn
    -0.63
     économies
    -0.63
     publiques
    -0.63
     étrangères
    -0.63
    Gele
    -0.63
    AccessorTable
    -0.61
    POSITIVE LOGITS
     frustration
    1.43
     frustrations
    1.38
    frust
    1.27
     Frust
    1.24
     frustrating
    1.23
     frustrated
    1.21
     frust
    1.20
    Frust
    1.16
     frustrate
    1.16
     frustra
    1.05
    Activations Density 0.001%

    No Known Activations