© 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. 4-CLT-HP
    4. 4411
    Prev
    Next
    INDEX
    Explanations

    and

    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
     StatefulWidget
    -0.56
    ContentAsync
    -0.48
    הערות
    -0.47
    yordu
    -0.46
    yorsunuz
    -0.46
    puts
    -0.42
    dafx
    -0.42
     hObject
    -0.41
     nhàng
    -0.41
    Pozri
    -0.40
    POSITIVE LOGITS
     Meilleures
    0.65
    UIControlState
    0.61
    EDEFAULT
    0.59
    :✨
    0.58
    Tembelea
    0.57
    apunov
    0.57
     airspace
    0.56
    #+#
    0.56
     commonest
    0.55
    sidemargin
    0.55
    Activations Density 0.003%

    No Known Activations