© 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. 5-CLT-HP
    7. 96059
    Prev
    Next
    INDEX
    Explanations

    Code, data, literature lists

    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
    while
    -0.46
    Réalisation
    -0.46
     while
    -0.45
    setof
    -0.45
     arranged
    -0.43
    abestanden
    -0.42
     gra
    -0.42
     rearranged
    -0.41
     f
    -0.41
    Distribuzione
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.89
     AspNetCore
    0.83
     CreateTagHelper
    0.79
    mybatisplus
    0.69
     EconPapers
    0.65
    aarrggbb
    0.63
    väg
    0.63
    تقاوى
    0.62
     présidenti
    0.60
     aveug
    0.60
    Activations Density 0.000%

    No Known Activations