© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44019
    Prev
    Next
    INDEX
    Explanations

    coma

    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
     basilica
    -1.00
    lech
    -0.96
    ագրություններ
    -0.77
     resourceCulture
    -0.56
    stretchr
    -0.56
    RectangleBorder
    -0.55
     coma
    -0.54
    ंदीखरीदारी
    -0.52
     FetchType
    -0.52
     linkovi
    -0.52
    POSITIVE LOGITS
    hythm
    0.52
     oprot
    0.51
    fusc
    0.51
    elegant
    0.48
     famí
    0.48
    oczes
    0.47
    uccino
    0.47
    ={`${
    0.46
    pasti
    0.46
    quels
    0.45
    Activations Density 1.651%

    No Known Activations