© 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. 0-CLT-HP
    7. 40468
    Prev
    Next
    INDEX
    Explanations

    Manufacturing and creation

    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
    rrggbb
    -0.74
     postings
    -0.63
    spoken
    -0.59
     resourceCulture
    -0.59
    ongo
    -0.55
    tonode
    -0.55
    EDEFAULT
    -0.54
    oyo
    -0.54
     AssemblyCulture
    -0.52
     effected
    -0.52
    POSITIVE LOGITS
    /**
    0.83
     sauvages
    0.77
     Diſ
    0.75
     pulito
    0.75
     fédé
    0.70
     universale
    0.69
     suprême
    0.69
     sufficiente
    0.68
     ainfi
    0.68
     titolata
    0.68
    Activations Density 0.586%

    No Known Activations