© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92793
    Prev
    Next
    INDEX
    Explanations

    all

    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
     all
    -0.83
    all
    -0.80
    All
    -0.69
     semua
    -0.65
    ALL
    -0.63
     allemaal
    -0.63
     suficientes
    -0.63
     in
    -0.63
     calientes
    -0.63
     to
    -0.60
    POSITIVE LOGITS
     resourceCulture
    0.61
    BagLayout
    0.60
     directions
    0.60
    cepted
    0.60
     their
    0.59
     the
    0.58
     Fayette
    0.58
    onya
    0.58
    thinkable
    0.58
    loro
    0.57
    Activations Density 0.027%

    No Known Activations