© 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. 4-CLT-HP
    7. 4606
    Prev
    Next
    INDEX
    Explanations

    the

    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
     المعيارى
    -0.71
    ⓧ
    -0.69
    StructEnd
    -0.69
     lendemain
    -0.68
    JspWriter
    -0.62
     Peker
    -0.60
     CONTRIBUTORS
    -0.60
     savons
    -0.60
    addCriterion
    -0.60
     rempliss
    -0.60
    POSITIVE LOGITS
     growth
    0.83
    WithIOException
    0.80
     development
    0.65
     spread
    0.64
     formation
    0.60
     rise
    0.59
    growth
    0.58
     practice
    0.56
     building
    0.56
     forming
    0.55
    Activations Density 0.001%

    No Known Activations