© 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. 73511
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    iros
    -0.48
     chain
    -0.40
    arent
    -0.40
    anus
    -0.39
     de
    -0.39
     bouch
    -0.37
     chains
    -0.37
     đ
    -0.37
    De
    -0.35
    rote
    -0.35
    POSITIVE LOGITS
     disambiguazione
    1.00
     resourceCulture
    0.93
     Roskov
    0.91
    脚注の使い方
    0.91
    AddTagHelper
    0.88
    DockStyle
    0.86
    CloseOperation
    0.79
     propOrder
    0.79
    ArrowToggle
    0.78
    цездатний
    0.77
    Activations Density 0.003%

    No Known Activations