© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14358
    Prev
    Next
    INDEX
    Explanations

    contest

    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
     competition
    -0.52
     compé
    -0.51
     contest
    -0.51
    ReusableCell
    -0.49
    synthesize
    -0.49
     exemplaires
    -0.48
     réflex
    -0.48
     saites
    -0.47
    Bakgrunnsstoff
    -0.47
     étend
    -0.46
    POSITIVE LOGITS
    tangentMode
    0.61
    ⓘ
    0.61
     itſelf
    0.60
     Papers
    0.59
     initComponents
    0.57
    ners
    0.57
    brite
    0.57
    encing
    0.56
    nodoc
    0.56
     Tyre
    0.56
    Activations Density 0.013%

    No Known Activations