© 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. 94385
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Composable
    -0.47
    beforeAll
    -0.47
    uts
    -0.45
    十
    -0.45
     Executive
    -0.45
     users
    -0.45
    索
    -0.44
    郡
    -0.44
    rent
    -0.43
    hof
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.94
    فایل‌لار
    0.75
    TemporalType
    0.73
    Carriera
    0.71
    expandindo
    0.70
     Wiktionnaire
    0.69
     становника
    0.69
    ็จ
    0.66
    Демографія
    0.66
     Sarm
    0.64
    Activations Density 0.000%

    No Known Activations