© 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. 0-CLT-HP
    7. 43213
    Prev
    Next
    INDEX
    Explanations

    Technical/professional topics

    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
     câbles
    -0.69
    يكب
    -0.68
     dizaines
    -0.65
     boî
    -0.60
     addressed
    -0.59
     accès
    -0.57
     Pristupljeno
    -0.56
     accéder
    -0.55
    ({
    -0.54
     оригіналу
    -0.54
    POSITIVE LOGITS
     BoxDecoration
    0.65
    y
    0.63
     InputDecoration
    0.57
    gory
    0.57
     Toko
    0.57
    i
    0.57
    e
    0.54
    sang
    0.53
    s
    0.53
    eing
    0.52
    Activations Density 0.058%

    No Known Activations