© 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. 20-CLT-HP
    7. 71790
    Prev
    Next
    INDEX
    Explanations

    Code/documentation snippets

    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
    enumii
    -0.66
    |}{$
    -0.53
    CppMethod
    -0.50
    habad
    -0.50
    encial
    -0.49
     schwarze
    -0.49
    BeginInit
    -0.48
    arpa
    -0.48
    enumi
    -0.47
    ligente
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.71
     }{@
    0.69
    حياتها
    0.68
    حياته
    0.57
    IsContent
    0.55
    脚注の使い方
    0.51
    CreateModel
    0.50
     vídeo
    0.50
     Icarus
    0.49
     Davi
    0.49
    Activations Density 0.002%

    No Known Activations