© 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. 53
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations involving variables

    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
     Infórmanos
    -0.83
     jsPsych
    -0.82
     Signalez
    -0.79
    featureID
    -0.77
    +#+
    -0.77
    rawDesc
    -0.75
    principalColumn
    -0.73
    elemField
    -0.73
     resourceCulture
    -0.71
    msgTypes
    -0.70
    POSITIVE LOGITS
     secours
    0.40
     Schmerzen
    0.38
     paura
    0.37
     eating
    0.37
     pourriez
    0.37
     mettez
    0.37
     douleurs
    0.37
     pitié
    0.36
     of
    0.36
     eat
    0.36
    Activations Density 5.815%

    No Known Activations