© 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. 6044
    Prev
    Next
    INDEX
    Explanations

    formal text snippets

    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
    قایناقلار
    -0.60
    WebVitals
    -0.57
    OnTop
    -0.50
    ThroughAttribute
    -0.49
     Commencez
    -0.48
     olympique
    -0.48
    NameInMap
    -0.48
     SearchView
    -0.48
     ExecuteAsync
    -0.47
    WTS
    -0.47
    POSITIVE LOGITS
    BeginContext
    0.66
     shortly
    0.58
     Acharya
    0.50
     Anno
    0.47
     تضيفلها
    0.47
    ISupport
    0.47
     Hellen
    0.46
    gonic
    0.46
     Kog
    0.45
    INERY
    0.45
    Activations Density 0.000%

    No Known Activations