© 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. 2298
    Prev
    Next
    INDEX
    Explanations

    say

    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
     how
    -0.51
     who
    -0.48
     कहा
    -0.47
     How
    -0.45
     frumos
    -0.43
     yourself
    -0.42
    ınt
    -0.42
    ỗ
    -0.40
     best
    -0.40
     reais
    -0.40
    POSITIVE LOGITS
    homonymie
    0.84
    WithIOException
    0.75
    sizeCache
    0.75
    TProtocol
    0.72
    unknownFields
    0.71
     ProtoMessage
    0.70
    ByExample
    0.65
    ConstraintMaker
    0.65
     Biôgrafia
    0.65
     iprot
    0.65
    Activations Density 0.000%

    No Known Activations