© 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. 4-CLT-HP
    7. 357
    Prev
    Next
    INDEX
    Explanations

    code, names, writing

    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
     AssemblyCulture
    -0.41
    multirow
    -0.34
    越高
    -0.34
    媲
    -0.32
    널
    -0.32
    uría
    -0.30
    koh
    -0.30
    ios
    -0.30
    Identyfik
    -0.30
     اغ
    -0.29
    POSITIVE LOGITS
    <bos>
    1.11
     AssemblyTitle
    0.71
     Paglinawan
    0.68
    findpost
    0.67
    enumi
    0.66
    SPJ
    0.62
    __':
    0.62
    UnusedPrivate
    0.62
    niająca
    0.60
     ujednoznacz
    0.60
    Activations Density 0.012%

    No Known Activations