© 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. 3063
    Prev
    Next
    INDEX
    Explanations

    Wilson

    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
    ]='\
    -0.77
     the
    -0.76
    ]='
    -0.68
    ]--;
    -0.65
     a
    -0.63
    ']=$
    -0.62
    ']='
    -0.61
    twas
    -0.61
    "]=
    -0.60
    +][
    -0.59
    POSITIVE LOGITS
    ,
    1.01
     refusé
    0.65
     payé
    0.63
     للمعارف
    0.63
     in
    0.61
     obligé
    0.61
     únicas
    0.60
     חיצוניים
    0.60
    featureID
    0.60
     disparu
    0.59
    Activations Density 0.002%

    No Known Activations