© 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. 4-CLT-HP
    7. 1774
    Prev
    Next
    INDEX
    Explanations

    architecture

    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
     كورة
    -0.53
    ismet
    -0.48
     söyl
    -0.46
    ///<
    -0.45
    move
    -0.45
     sudad
    -0.44
    estra
    -0.43
     peores
    -0.43
    EFIAPI
    -0.43
     mauvaises
    -0.43
    POSITIVE LOGITS
    ViewFeatures
    0.90
    tonode
    0.88
    StoryboardSegue
    0.71
    saraba
    0.68
     nahilalakip
    0.68
    InstrumentedTest
    0.64
    BeginContext
    0.63
    AddTagHelper
    0.62
    lgari
    0.62
     الرياضيه
    0.62
    Activations Density 0.003%

    No Known Activations