© 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. 20-CLT-HP
    7. 73704
    Prev
    Next
    INDEX
    Explanations

    change

    np_max-act-logits · 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
    sizeCache
    -0.63
    Personendaten
    -0.62
    errHandler
    -0.61
     nakalista
    -0.60
    contentLoaded
    -0.59
     StatelessWidget
    -0.56
     ModelExpression
    -0.56
    TagHelper
    -0.55
    ViewFeatures
    -0.55
    킴
    -0.54
    POSITIVE LOGITS
     calendriers
    0.52
     nawr
    0.50
     Wissenschaften
    0.45
    ảm
    0.44
     Deliber
    0.44
    ///</
    0.44
    casila
    0.44
    pdp
    0.43
    quanto
    0.43
    java
    0.43
    Activations Density 0.000%

    No Known Activations