© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12969
    Prev
    Next
    INDEX
    Explanations

    sun/sky

    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
    ViewChild
    -0.59
     NSCoder
    -0.57
    طوب
    -0.47
    पया
    -0.47
     الاطلاع
    -0.45
    تقاوى
    -0.44
    UIControlState
    -0.44
    EndInit
    -0.44
    benar
    -0.43
    BeginInit
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.75
    xture
    0.68
    mpto
    0.60
    rungsseite
    0.60
     Efq
    0.59
    KEYCODE
    0.57
    pēc
    0.55
    횟
    0.55
     дописавши
    0.54
    IORITY
    0.54
    Activations Density 0.012%

    No Known Activations