© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97354
    Prev
    Next
    INDEX
    Explanations

    nighttime

    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
     IndexPath
    -0.68
    iostream
    -0.56
     disambiguazione
    -0.55
    GNUC
    -0.54
    RoutingModule
    -0.54
     الحره
    -0.52
     Assn
    -0.52
    IntentFilter
    -0.52
     Spectrometry
    -0.51
    IContainer
    -0.50
    POSITIVE LOGITS
    labus
    0.69
    Jeografia
    0.60
    time
    0.56
    ViewImports
    0.47
    ContentAsync
    0.45
     ddelweddau
    0.45
    νονται
    0.45
    neous
    0.44
    地说道
    0.44
    +#+#
    0.43
    Activations Density 0.001%

    No Known Activations