© 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. 13352
    Prev
    Next
    INDEX
    Explanations

    the tens digit and nurseries

    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
    Geplaatst
    -0.77
    ValueStyle
    -0.76
    RectangleBorder
    -0.72
    ArrowToggle
    -0.72
    principalTable
    -0.71
    ergies
    -0.71
     Roskov
    -0.69
    matchCondition
    -0.66
     Мексичка
    -0.66
     prisonniers
    -0.64
    POSITIVE LOGITS
     kuy
    0.45
     money
    0.41
    ItemSelected
    0.39
     calldata
    0.38
    ジュアル
    0.36
    レイ
    0.36
    dac
    0.35
    риди
    0.35
    mappedBy
    0.35
    __((
    0.35
    Activations Density 0.016%

    No Known Activations