© 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. 5-CLT-HP
    7. 5047
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Te
    -0.59
     Ever
    -0.54
    ^*)
    -0.54
    itoriale
    -0.53
    sy
    -0.53
     Most
    -0.52
    san
    -0.50
     App
    -0.50
     "_"
    -0.50
    jack
    -0.49
    POSITIVE LOGITS
     EconPapers
    0.77
     MainAxisSize
    0.62
    MENAFN
    0.58
    ThroughAttribute
    0.57
     AssemblyCulture
    0.57
     שוליים
    0.56
    apimachinery
    0.56
    AnimationsModule
    0.55
     Normdatei
    0.54
     ↓,
    0.52
    Activations Density 0.003%

    No Known Activations