© 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. 4-CLT-HP
    7. 4691
    Prev
    Next
    INDEX
    Explanations

    behavioral

    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
     للمعارف
    -0.71
    ParallelGroup
    -0.59
     économiques
    -0.57
    허
    -0.56
    <caption>
    -0.54
    addGap
    -0.50
     européennes
    -0.50
     genoux
    -0.49
    +#+#
    -0.49
    IContainer
    -0.48
    POSITIVE LOGITS
    存于互联网档案馆
    0.61
     مشين
    0.56
     changes
    0.56
     invokingState
    0.54
     AssemblyProduct
    0.53
     '{@
    0.53
    mals
    0.52
     behavioral
    0.52
     TType
    0.51
     Changes
    0.50
    Activations Density 0.002%

    No Known Activations