© 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. 1424
    Prev
    Next
    INDEX
    Explanations

    variable

    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
     variable
    -1.16
    variable
    -0.89
     Variable
    -0.72
    Variable
    -0.71
     variabel
    -0.61
     VARIABLE
    -0.52
     adjustable
    -0.50
    ing
    -0.49
     fixed
    -0.48
    VARIABLE
    -0.47
    POSITIVE LOGITS
    ImageContext
    0.84
    DockStyle
    0.82
    ItemBackground
    0.78
     незавершена
    0.76
    WebElementEntity
    0.75
     EconPapers
    0.74
    rrggbb
    0.73
    ]--;
    0.71
     Vivid
    0.69
    Приятного
    0.68
    Activations Density 0.523%

    No Known Activations