© 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. 96
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical modeling and estimation processes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     almohada
    -0.75
     manguera
    -0.74
     satisfecho
    -0.72
     fieltro
    -0.71
     rodilla
    -0.70
     botella
    -0.69
     desmotivaciones
    -0.69
     toalla
    -0.69
     tacón
    -0.68
    thâu
    -0.67
    POSITIVE LOGITS
    PI
    0.65
    CP
    0.65
     C
    0.64
    F
    0.63
    AP
    0.63
    CL
    0.63
    CS
    0.62
    W
    0.62
    FT
    0.61
    CM
    0.61
    Activations Density 7.767%

    No Known Activations