Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45164
    Prev
    Next
    INDEX
    Explanations

    it

    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
    verwijspagina
    -0.66
     croire
    -0.64
     NUKAT
    -0.64
     venons
    -0.62
    interopRequire
    -0.62
    grès
    -0.61
    Espèce
    -0.60
    érables
    -0.58
     extérieurs
    -0.58
    Zitat
    -0.57
    POSITIVE LOGITS
     the
    0.72
     its
    0.68
     they
    0.57
     that
    0.57
     what
    0.57
     both
    0.54
     there
    0.54
     raised
    0.51
    titleMargin
    0.50
     received
    0.49
    Activations Density 0.087%

    No Known Activations