© 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. 38538
    Prev
    Next
    INDEX
    Explanations

    several

    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
    several
    -1.70
    Several
    -1.68
     several
    -1.58
     Several
    -1.58
     plusieurs
    -1.26
     vários
    -1.13
     flera
    -1.13
     feveral
    -1.08
     várias
    -1.07
     varios
    -1.06
    POSITIVE LOGITS
     hundred
    0.98
     thousand
    0.85
    s
    0.75
     types
    0.69
     million
    0.68
    hundred
    0.63
     Hundred
    0.63
    nya
    0.62
    Hundred
    0.62
     important
    0.58
    Activations Density 0.058%

    No Known Activations