© 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. 5-CLT-HP
    7. 5368
    Prev
    Next
    INDEX
    Explanations

    from

    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
    帖最后由
    -0.64
     AssemblyCompany
    -0.56
     swearing
    -0.48
     umana
    -0.47
    thansa
    -0.46
    \|^{
    -0.45
     mío
    -0.45
     launching
    -0.44
    ENDING
    -0.44
     uttering
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.65
    esModule
    0.62
     initComponents
    0.62
     '\\;'
    0.58
    ueba
    0.55
     désolés
    0.54
    multer
    0.54
    FieldNumber
    0.53
    rodalom
    0.53
    memcmp
    0.52
    Activations Density 0.001%

    No Known Activations