© 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. 6152
    Prev
    Next
    INDEX
    Explanations

    Greek

    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
    Negative Logits
     expédié
    -0.50
     erstmals
    -0.50
     terciopelo
    -0.47
    anterie
    -0.45
     cinq
    -0.45
     IRS
    -0.44
    ulement
    -0.44
    ایش
    -0.44
     urbanas
    -0.43
    timber
    -0.43
    POSITIVE LOGITS
     оригіналу
    0.97
    PerformLayout
    0.70
     مرئيه
    0.66
    ThroughAttribute
    0.64
    ]))
    0.59
     Waray
    0.59
    onedDateTime
    0.59
     defaultstate
    0.58
    awtextra
    0.57
    WritableDatabase
    0.57
    Activations Density 0.003%

    No Known Activations