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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11554
    Prev
    Next
    INDEX
    Explanations

    long duration/physics

    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
    IntoConstraints
    -0.86
     NSCoder
    -0.82
    running
    -0.75
    sidemargin
    -0.73
     AttributeSet
    -0.73
    BeginContext
    -0.72
    setVerticalGroup
    -0.71
    HomeAsUpEnabled
    -0.69
     للاسماء
    -0.69
    oredCriteria
    -0.69
    POSITIVE LOGITS
    vasti
    0.43
    ленное
    0.42
     effort
    0.42
    ernan
    0.41
     WaitForSeconds
    0.41
    <bos>
    0.41
     vụ
    0.41
    arbeit
    0.40
     among
    0.39
    +
    0.39
    Activations Density 0.019%

    No Known Activations