© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4458
    Prev
    Next
    INDEX
    Explanations

    is

    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
     first
    -0.58
    :
    -0.49
     firstly
    -0.49
    DoubleQuotes
    -0.47
     primeiras
    -0.46
     primero
    -0.45
     första
    -0.44
     første
    -0.44
    first
    -0.44
     أول
    -0.44
    POSITIVE LOGITS
    хьтан
    0.96
    GEBURTSDATUM
    0.96
     nakalista
    0.86
     Wiktionnaire
    0.80
    oredCriteria
    0.79
    Vidite
    0.78
     Италијани
    0.76
     transfieras
    0.76
     فريبيس
    0.76
    новниш
    0.76
    Activations Density 0.005%

    No Known Activations