© 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. 94288
    Prev
    Next
    INDEX
    Explanations

    random varied topics

    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
     AssemblyCulture
    -1.00
    TagMode
    -0.78
     GenerationType
    -0.77
     Мексичка
    -0.76
     kasarigan
    -0.71
     CreateTagHelper
    -0.68
    ]")]
    -0.68
     réfrig
    -0.66
    RefNanny
    -0.64
    ⓧ
    -0.64
    POSITIVE LOGITS
     conditions
    0.61
     reservations
    0.58
     obstacles
    0.58
     labels
    0.56
     formulas
    0.54
     filters
    0.54
     barriers
    0.54
     hesitation
    0.52
     filtering
    0.52
     parameters
    0.52
    Activations Density 0.014%

    No Known Activations