© 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. 13402
    Prev
    Next
    INDEX
    Explanations

    complete sentences

    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
    first
    -0.88
    abord
    -0.88
     first
    -0.88
    начала
    -0.84
    первых
    -0.82
     primero
    -0.81
     сначала
    -0.77
    Firstly
    -0.75
     Firstly
    -0.73
     primeiro
    -0.73
    POSITIVE LOGITS
    IsMutable
    0.89
    MergeFrom
    0.71
     Numerade
    0.63
    CopyWith
    0.59
    󠁢
    0.57
    رشف
    0.57
     للاسماء
    0.57
     שוליים
    0.57
    TestTools
    0.54
    rawDesc
    0.52
    Activations Density 0.029%

    No Known Activations