© 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. 42806
    Prev
    Next
    INDEX
    Explanations

    sprig

    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
    GraphicsUnit
    -0.86
    yntaxException
    -0.79
     sprig
    -0.78
    eries
    -0.76
     Meksiku
    -0.76
    mybatisplus
    -0.75
    erals
    -0.74
     незавершена
    -0.73
     Infórmanos
    -0.73
     Bodies
    -0.72
    POSITIVE LOGITS
     of
    0.61
     albicans
    0.47
    hObject
    0.45
    numerusform
    0.43
    کد
    0.39
     Gode
    0.36
     منها
    0.36
    acaktır
    0.36
    Prerequisite
    0.36
     (
    0.35
    Activations Density 1.845%

    No Known Activations