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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11800
    Prev
    Next
    INDEX
    Explanations

    0

    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
    ppich
    -0.60
    odeon
    -0.55
    acje
    -0.55
    ilene
    -0.55
     hình
    -0.54
    Portály
    -0.52
    ಾನ
    -0.52
     Max
    -0.52
    fxml
    -0.52
     subject
    -0.50
    POSITIVE LOGITS
    ंदीखरीदारी
    0.75
    twimg
    0.65
    apunov
    0.57
     ComVisible
    0.56
     Majesté
    0.55
    énéral
    0.55
     Lordships
    0.55
     Roskov
    0.54
    ArgumentParser
    0.53
    httphttps
    0.53
    Activations Density 0.022%

    No Known Activations