© 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. 253
    Prev
    Next
    INDEX
    Explanations

    scientific terms or phrases related to analysis and evaluation

    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
     ainfi
    -0.69
     purpoſe
    -0.69
     ſich
    -0.68
     plufieurs
    -0.67
    IntoConstraints
    -0.67
    XmlAccessType
    -0.66
     ProtoMessage
    -0.66
     miniaturka
    -0.66
     ſein
    -0.66
     geſ
    -0.66
    POSITIVE LOGITS
     arşivlendi
    0.59
    󠁿
    0.50
    CJK
    0.44
    ธ์
    0.42
    ">(</
    0.42
    าสตร์
    0.39
    :"-"`
    0.38
    なく
    0.36
    ์
    0.36
     the
    0.35
    Activations Density 20.618%

    No Known Activations