© 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. 0-CLT-HP
    7. 38803
    Prev
    Next
    INDEX
    Explanations

    studies

    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
     studies
    -3.33
    studies
    -2.98
     Studies
    -2.83
     STUDIES
    -2.77
    Studies
    -2.67
     études
    -2.08
    STUDIES
    -2.02
     estudos
    -2.00
     estudios
    -1.98
     Studien
    -1.59
    POSITIVE LOGITS
    Бахар
    0.52
    heet
    0.49
    hells
    0.49
     بيها
    0.47
    __((
    0.47
    có
    0.47
    warnai
    0.47
    hell
    0.46
    barung
    0.46
     worth
    0.45
    Activations Density 0.078%

    No Known Activations