© 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. 0-CLT-HP
    7. 40634
    Prev
    Next
    INDEX
    Explanations

    business and sales

    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
    can
    -0.90
    Can
    -0.73
    stack
    -0.67
     slices
    -0.63
     letteratura
    -0.60
     literature
    -0.60
    vendor
    -0.59
    slice
    -0.59
    literature
    -0.56
     sliced
    -0.55
    POSITIVE LOGITS
     AttributeSet
    0.91
    TestingModule
    0.84
    expandindo
    0.82
     كومونز
    0.79
     TabLayout
    0.71
     linkovi
    0.71
     IBOutlet
    0.69
    ised
    0.68
     StatefulWidget
    0.66
    eer
    0.66
    Activations Density 0.307%

    No Known Activations