© 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. 2010
    Prev
    Next
    INDEX
    Explanations

    code and numerical data

    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
    spesies
    -0.48
     Danza
    -0.47
    bollah
    -0.46
     bless
    -0.45
     ordination
    -0.43
    する方法
    -0.43
     responsibly
    -0.42
     코드
    -0.42
    nemen
    -0.41
     Ause
    -0.41
    POSITIVE LOGITS
    RefNanny
    0.66
    клопе
    0.65
     تانيه
    0.63
     disambiguazione
    0.63
    例文帳に追加
    0.63
     يتيمه
    0.62
     désolés
    0.60
    ".
    0.58
    Données
    0.57
     незавершена
    0.57
    Activations Density 0.019%

    No Known Activations