© 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. 4-CLT-HP
    7. 3130
    Prev
    Next
    INDEX
    Explanations

    sp

    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
     تضيفلها
    -0.67
     bail
    -0.63
    CardContent
    -0.58
     gle
    -0.57
     Majefty
    -0.55
    født
    -0.54
     Mlle
    -0.53
    ……"
    -0.53
    ."],
    -0.52
     Pah
    -0.51
    POSITIVE LOGITS
    IContainer
    0.51
    ondy
    0.50
    sis
    0.48
    ándola
    0.46
     esetben
    0.45
     composés
    0.45
     Gottes
    0.44
     Christi
    0.44
    ậc
    0.43
    ándolos
    0.43
    Activations Density 0.007%

    No Known Activations