© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43427
    Prev
    Next
    INDEX
    Explanations

    Code/foreign names

    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
     Jie
    -2.05
    jie
    -1.37
    Jie
    -1.30
     jie
    -1.09
    aarrggbb
    -0.84
    GEBURTSDATUM
    -0.78
     oprot
    -0.76
     purpoſe
    -0.76
     raiſ
    -0.71
     diſt
    -0.70
    POSITIVE LOGITS
     незавершена
    0.52
    cydow
    0.44
     StatelessWidget
    0.42
    WriteTagHelper
    0.42
    y
    0.42
     zaak
    0.41
     szóci
    0.41
    autoconfigure
    0.40
    my
    0.39
    min
    0.39
    Activations Density 1.658%

    No Known Activations