© 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. 0-CLT-HP
    7. 38439
    Prev
    Next
    INDEX
    Explanations

    vegetables

    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
     spinach
    -0.97
     zucchini
    -0.93
     Spinach
    -0.93
    Greens
    -0.92
     requestCode
    -0.90
     Greens
    -0.81
     purpoſe
    -0.80
     greens
    -0.78
    NOPQRST
    -0.78
    OGND
    -0.77
    POSITIVE LOGITS
     same
    0.47
    oid
    0.45
    same
    0.44
    tit
    0.43
     first
    0.43
    graphiques
    0.41
    ."
    0.41
     then
    0.40
     delivered
    0.40
    .
    0.40
    Activations Density 1.376%

    No Known Activations