© 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-2-2B
    5. 5-CLT-HP
    7. 5997
    Prev
    Next
    INDEX
    Explanations

    molecular

    np_max-act · gemini-2.0-flash
    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
     colpa
    -0.60
     refroidissement
    -0.60
     résolution
    -0.60
     waard
    -0.59
     ''){
    -0.59
     mauva
    -0.58
    XmlEnum
    -0.57
     découver
    -0.56
     nødven
    -0.56
     rapports
    -0.56
    POSITIVE LOGITS
    ValueStyle
    0.69
    numerusform
    0.59
    rih
    0.52
     doPost
    0.51
     الحره
    0.51
    noh
    0.50
     setPassword
    0.50
     demonstration
    0.49
     Diri
    0.49
    enumi
    0.48
    Activations Density 0.008%

    No Known Activations