© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10019
    Prev
    Next
    INDEX
    Explanations

    left/right

    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
    viewDidLoad
    -0.59
     boots
    -0.57
     botas
    -0.54
     وحد
    -0.49
     schoenen
    -0.47
     eccl
    -0.47
    كذا
    -0.46
     smartly
    -0.45
    غيل
    -0.45
    VELOP
    -0.44
    POSITIVE LOGITS
    +#+#
    0.77
     Roskov
    0.72
     חיצוניים
    0.66
    oa̍t
    0.65
    ьаж
    0.65
     Walkover
    0.63
     تضيفلها
    0.60
     lymphatic
    0.59
    posedge
    0.59
    ⓧ
    0.59
    Activations Density 0.096%

    No Known Activations