© 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. 0-CLT-HP
    7. 95435
    Prev
    Next
    INDEX
    Explanations

    div

    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
     divides
    -1.29
    divided
    -1.23
     divided
    -1.20
     Divided
    -1.20
     divide
    -1.15
     dividido
    -1.14
    divide
    -1.10
     dividida
    -1.07
     dividing
    -1.06
     divisions
    -1.05
    POSITIVE LOGITS
     a
    0.60
     an
    0.56
    a
    0.55
     P
    0.54
     et
    0.54
    e
    0.52
     her
    0.52
     C
    0.51
     list
    0.50
     D
    0.50
    Activations Density 0.092%

    No Known Activations