© 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. 45382
    Prev
    Next
    INDEX
    Explanations

    believer

    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
     Galleries
    -0.92
     galleries
    -0.78
    lography
    -0.73
    DockStyle
    -0.69
     bParam
    -0.68
    ۜ
    -0.64
    WebServlet
    -0.63
    saraba
    -0.63
     møte
    -0.63
     mourut
    -0.61
    POSITIVE LOGITS
    ma
    0.63
    oma
    0.54
    lio
    0.52
     Testamento
    0.50
    ️
    0.49
     tra
    0.48
    mad
    0.47
    ema
    0.47
    sprogram
    0.47
    illo
    0.46
    Activations Density 0.079%

    No Known Activations