© 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. 49
    Prev
    Next
    INDEX
    Explanations

    complex chemical compounds and their related structural data

    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
    httphttps
    -1.20
     мәкал
    -1.17
    IsContent
    -1.11
    OGND
    -1.11
     ſehr
    -1.07
    ſchaft
    -1.05
     zwiſchen
    -1.04
    ſehen
    -1.03
    <unused8>
    -1.02
    <unused16>
    -1.02
    POSITIVE LOGITS
    a
    0.33
    2
    0.29
    D
    0.28
    C
    0.27
    3
    0.26
    ,
    0.26
     Independencia
    0.25
    5
    0.24
     Andalucía
    0.24
    z
    0.23
    Activations Density 5.899%

    No Known Activations