© 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. 1-CLT-HP
    7. 743
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    rungsseite
    -0.85
    ंदीखरीदारी
    -0.79
     calendriers
    -0.76
    WithIOException
    -0.75
    ISupport
    -0.74
    SBATCH
    -0.74
    bitField
    -0.73
     surla
    -0.72
     CreateTagHelper
    -0.71
    ItemBackground
    -0.71
    POSITIVE LOGITS
    /
    0.68
     can
    0.63
     /
    0.57
     multi
    0.55
     K
    0.54
     not
    0.54
     non
    0.53
     ro
    0.52
     loss
    0.52
     D
    0.52
    Activations Density 0.065%

    No Known Activations