© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97325
    Prev
    Next
    INDEX
    Explanations

    worst

    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
     worst
    -1.72
     Worst
    -1.58
     worse
    -1.53
    worst
    -1.49
    worse
    -1.44
    Worst
    -1.35
     Worse
    -1.29
     peor
    -1.20
     peggio
    -1.16
    Worse
    -1.09
    POSITIVE LOGITS
    ousing
    0.41
     assignment
    0.41
     night
    0.41
    Identyfik
    0.41
    ällning
    0.40
    :✨
    0.39
     að
    0.38
    Grounded
    0.38
    atguigu
    0.38
     extension
    0.37
    Activations Density 0.052%

    No Known Activations