© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15596
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
     data
    -0.98
     Data
    -0.90
    data
    -0.80
     DATA
    -0.76
    Data
    -0.76
     Daten
    -0.70
    数据
    -0.68
     데이터
    -0.63
    數據
    -0.62
     datos
    -0.61
    POSITIVE LOGITS
    Tikang
    0.72
     autorytatywna
    0.67
     transfieras
    0.61
    AddTagHelper
    0.61
    Sucesor
    0.60
    >{@
    0.59
    RTLI
    0.56
     Reverso
    0.56
    ReusableCell
    0.55
    featureID
    0.55
    Activations Density 0.156%

    No Known Activations