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. 4-CLT-HP
    4. 3711
    Prev
    Next
    INDEX
    Explanations

    Introducing a topic/information

    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
    slack
    -0.48
    FirstResponder
    -0.44
    raim
    -0.44
    ecé
    -0.44
     Traduction
    -0.44
    ViewComponent
    -0.43
    checkOut
    -0.43
    LoginComponent
    -0.43
    คิด
    -0.42
    keyColumn
    -0.42
    POSITIVE LOGITS
     them
    0.78
     the
    0.76
     him
    0.71
     Paglinawan
    0.69
     cref
    0.67
     createContext
    0.67
     it
    0.62
     nahilalakip
    0.60
     calendriers
    0.59
     مشين
    0.57
    Activations Density 0.002%

    No Known Activations