© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11585
    Prev
    Next
    INDEX
    Explanations

    Duffy

    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
     Duffy
    -0.93
    Duff
    -0.69
    ing
    -0.53
    es
    -0.52
    ira
    -0.51
    f
    -0.51
    loys
    -0.50
     domain
    -0.50
    er
    -0.49
    p
    -0.48
    POSITIVE LOGITS
     betweenstory
    0.73
    adeloupe
    0.60
     auroit
    0.60
     peindre
    0.60
    galus
    0.59
    ContentAsync
    0.59
     resourceCulture
    0.59
     chi̍t
    0.58
     '\\;'
    0.57
     skydd
    0.57
    Activations Density 0.008%

    No Known Activations