© 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. 6178
    Prev
    Next
    INDEX
    Explanations

    gratitude and acknowledgement

    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
    farwyddwr
    -0.66
    nanoTime
    -0.66
     wireType
    -0.65
     épaules
    -0.63
    сылкі
    -0.61
     @"/
    -0.61
    Autoritní
    -0.57
    Personendaten
    -0.56
    oprot
    -0.56
    featureID
    -0.56
    POSITIVE LOGITS
    HasForeignKey
    0.56
     liever
    0.54
    mentation
    0.54
    Rifer
    0.53
    tetés
    0.52
    liziert
    0.49
    omers
    0.49
     borrowed
    0.48
    otations
    0.48
     remittances
    0.47
    Activations Density 0.002%

    No Known Activations