© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 5041
    Prev
    Next
    INDEX
    Explanations

    live

    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
    ējās
    -0.64
     informée
    -0.59
    sdag
    -0.57
     entour
    -0.56
     begonnen
    -0.54
    medriver
    -0.53
     penjara
    -0.53
     consultato
    -0.53
     Audiodateien
    -0.52
     inégal
    -0.52
    POSITIVE LOGITS
    weight
    0.66
    makeConstraints
    0.62
    出版年
    0.62
    foot
    0.59
    footed
    0.54
    forward
    0.52
    IContainer
    0.52
    fire
    0.51
    lihood
    0.51
    CppCodeGen
    0.51
    Activations Density 0.009%

    No Known Activations