© 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. 3226
    Prev
    Next
    INDEX
    Explanations

    timely

    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
    matchCondition
    -0.93
     noDo
    -0.86
    ValueStyle
    -0.81
    ftagPool
    -0.76
    tagHelperRunner
    -0.76
     surla
    -0.73
     Waray
    -0.71
     uſed
    -0.71
    Controllo
    -0.71
     myſelf
    -0.70
    POSITIVE LOGITS
     way
    0.56
     manner
    0.48
     basis
    0.46
     manier
    0.45
     sposób
    0.43
     manera
    0.43
     fashion
    0.43
     Weise
    0.42
     parent
    0.40
    nungs
    0.40
    Activations Density 0.003%

    No Known Activations