© 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. 95245
    Prev
    Next
    INDEX
    Explanations

    surveys and data analysis

    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
     שוליים
    -0.67
    UserScript
    -0.56
    éndole
    -0.50
     estekak
    -0.50
    Cyfeiriadau
    -0.49
    σιο
    -0.48
     فريبيس
    -0.47
     ویکی‌آمباردا
    -0.47
    ίναι
    -0.47
     comuniques
    -0.46
    POSITIVE LOGITS
     survey
    0.59
     all
    0.57
     Survey
    0.56
     calendriers
    0.55
     aerial
    0.55
     ElementRef
    0.54
    bruik
    0.54
     rospy
    0.53
    INGHAM
    0.52
     reconnaissance
    0.52
    Activations Density 0.001%

    No Known Activations