© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 426
    Prev
    Next
    INDEX
    Explanations

    references to psychological themes related to personal experiences and emotional depth in storytelling

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     fraude
    -0.53
     coopération
    -0.53
    ########.
    -0.53
    Emergency
    -0.52
     Emergency
    -0.51
     gouver
    -0.51
     subsidi
    -0.51
     emergency
    -0.50
     AssemblyCulture
    -0.50
     unemployment
    -0.49
    POSITIVE LOGITS
     narrative
    0.65
     subtle
    0.64
     subtly
    0.63
     evocative
    0.60
     lyrical
    0.59
     captivating
    0.57
     sumptuous
    0.57
     brilliantly
    0.56
     nuanced
    0.56
     reminiscent
    0.55
    Activations Density 2.583%

    No Known Activations