© 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. 94182
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     uſed
    -0.77
     Efq
    -0.73
     ſeveral
    -0.66
     myſelf
    -0.66
     مشين
    -0.64
     HttpNotFound
    -0.60
     Quelques
    -0.59
     $_"
    -0.57
     ſome
    -0.57
     deſt
    -0.56
    POSITIVE LOGITS
    MergeFrom
    0.60
    mazoo
    0.56
    WithMany
    0.56
    :✨
    0.55
    vmware
    0.50
    ритори
    0.47
    createCanvas
    0.46
    SharedDtor
    0.45
     onBackPressed
    0.45
    InjectAttribute
    0.45
    Activations Density 0.004%

    No Known Activations