© 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. 185
    Prev
    Next
    INDEX
    Explanations

    statements or phrases that present explanations or reasons

    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
    RegressionTest
    -0.51
    uginosa
    -0.48
     bezeichneter
    -0.46
    antaine
    -0.46
    ufact
    -0.46
     valueForKey
    -0.45
     صوتيه
    -0.45
    LookAnd
    -0.44
     IBOutlet
    -0.44
    AutoScale
    -0.43
    POSITIVE LOGITS
     Esto
    0.56
     وهذا
    0.56
     is
    0.55
     mikä
    0.55
     happens
    0.48
     proves
    0.46
    這是
    0.46
     Tämä
    0.45
     Isso
    0.44
     což
    0.44
    Activations Density 2.453%

    No Known Activations