© 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. 0-CLT-HP
    7. 93064
    Prev
    Next
    INDEX
    Explanations

    countries

    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
     Chilean
    -1.05
     chilena
    -0.75
     chileno
    -0.71
     Lithuanian
    -0.68
     Prussian
    -0.67
     avoient
    -0.66
     myſelf
    -0.65
     Spani
    -0.63
     îna
    -0.63
     cauza
    -0.63
    POSITIVE LOGITS
    MessageTagHelper
    0.71
     ujednoznacz
    0.67
    BeginInit
    0.59
    RTHOOK
    0.58
    saraba
    0.53
    XtraBars
    0.53
     EClass
    0.53
    XtraEditors
    0.52
     hum
    0.52
    resizingMask
    0.52
    Activations Density 0.131%

    No Known Activations