© 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. 2144
    Prev
    Next
    INDEX
    Explanations

    technical documentation snippets

    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
    addContainerGap
    -0.52
     gloire
    -0.46
    достатки
    -0.41
     Outros
    -0.40
     môi
    -0.40
    thu
    -0.40
    져
    -0.39
    nson
    -0.39
    endum
    -0.38
    сама
    -0.38
    POSITIVE LOGITS
     Мексичка
    1.12
    setVerticalGroup
    1.09
    :✨
    1.07
    LookAnd
    0.96
     Савезне
    0.90
     للاسماء
    0.88
    <bos>
    0.85
    Personensuche
    0.84
    EndGlobalSection
    0.83
    webElementXpaths
    0.83
    Activations Density 0.000%

    No Known Activations