© 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. 90905
    Prev
    Next
    INDEX
    Explanations

    lowercase "i" or "e"

    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
    .
    -0.88
     '
    -0.59
     
    -0.59
     (
    -0.58
     a
    -0.57
    ↵↵
    -0.57
    ↵
    -0.56
    !
    -0.55
     "
    -0.54
    <eos>
    -0.52
    POSITIVE LOGITS
     avoient
    1.06
     Roskov
    1.02
     Мексичка
    1.01
     ModelExpression
    0.93
     myſelf
    0.93
     étoient
    0.92
     iſt
    0.90
     Efq
    0.90
     Monfieur
    0.89
     Houſe
    0.88
    Activations Density 0.002%

    No Known Activations