© 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. 6127
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    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
     façons
    -0.56
    getJSONArray
    -0.50
    protos
    -0.50
    :^{
    -0.48
    readString
    -0.48
     oportunidade
    -0.48
     initComponents
    -0.48
     <<<<<<<<<<<<<<
    -0.47
    tagHelper
    -0.47
     normals
    -0.47
    POSITIVE LOGITS
    intéress
    0.55
    sized
    0.51
    AxisAlignment
    0.50
     seduced
    0.49
    LayoutConstraint
    0.48
    ParallelGroup
    0.48
    قایناق‌لار
    0.47
     LENGTH
    0.47
    players
    0.47
    parsedMessage
    0.46
    Activations Density 0.002%

    No Known Activations