© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76926
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.62
     disponibilités
    -0.55
     springfox
    -0.54
    tagHelperRunner
    -0.52
     Савезне
    -0.49
     veille
    -0.49
    Билгалдахарш
    -0.48
    EndContext
    -0.47
    cillo
    -0.47
     cref
    -0.47
    POSITIVE LOGITS
    InputBorder
    0.58
     Malaysian
    0.54
    actionMode
    0.53
     للمعارف
    0.52
     postIndex
    0.50
    malle
    0.50
     ashore
    0.49
     Maine
    0.48
    tvguidetime
    0.48
    RetentionPolicy
    0.47
    Activations Density 0.000%

    No Known Activations