Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74319
    Prev
    Next
    INDEX
    Explanations

    kar/ker/ko

    np_max-act-logits · 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
    :✨
    -0.73
    OGND
    -0.69
    __(/*!
    -0.68
    VersionUID
    -0.63
     arşivlendi
    -0.62
     CIM
    -0.59
    Hochspringen
    -0.57
    +#+#
    -0.57
    InputBorder
    -0.57
    HasForeignKey
    -0.54
    POSITIVE LOGITS
     Hiring
    0.54
     MotionEvent
    0.52
    клопе
    0.49
    RetentionPolicy
    0.49
    XmlType
    0.49
    addCriterion
    0.47
    stdafx
    0.47
     hiring
    0.47
    EditorBrowsable
    0.44
    mic
    0.44
    Activations Density 0.001%

    No Known Activations