© 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. 5-CLT-HP
    7. 94511
    Prev
    Next
    INDEX
    Explanations

    grades

    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
    top
    -0.43
    bad
    -0.41
    el
    -0.41
    don
    -0.39
    Top
    -0.37
    one
    -0.37
    bind
    -0.37
     Top
    -0.36
    it
    -0.36
    ImageContext
    -0.35
    POSITIVE LOGITS
     EconPapers
    0.95
    findpost
    0.90
     myſelf
    0.90
    RenderAtEndOf
    0.90
    تقاوى
    0.86
    expandindo
    0.85
    ScopeManager
    0.83
     Audiodateien
    0.82
    GOTREF
    0.82
     createState
    0.82
    Activations Density 0.000%

    No Known Activations