© 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. 0-CLT-HP
    7. 43191
    Prev
    Next
    INDEX
    Explanations

    true

    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
    true
    -1.36
     true
    -1.27
    True
    -1.04
     True
    -0.96
     TRUE
    -0.93
     verdadero
    -0.91
     verdadera
    -0.90
     vraie
    -0.89
     verdade
    -0.87
     vrai
    -0.85
    POSITIVE LOGITS
    UrlResolution
    0.61
    Xna
    0.60
    UniformLocation
    0.60
    EndGlobalSection
    0.58
    IActionResult
    0.58
    IBOutlet
    0.56
    multicolumn
    0.56
    SceneManagement
    0.55
     saites
    0.55
    IsContent
    0.55
    Activations Density 0.112%

    No Known Activations