© 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. 94813
    Prev
    Next
    INDEX
    Explanations

    change

    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
    GOTREF
    -0.73
     ProtoMessage
    -0.68
     instead
    -0.65
    GenerationType
    -0.64
     InputDecoration
    -0.63
    matan
    -0.60
    instead
    -0.57
     مشين
    -0.56
    fony
    -0.54
    stuk
    -0.54
    POSITIVE LOGITS
     ujednoznacz
    0.69
     bells
    0.57
    #+#
    0.54
     للمعارف
    0.54
     AssemblyCulture
    0.53
     ffilmiau
    0.50
     ModelExpression
    0.50
     wells
    0.50
    しかったです
    0.49
    ंदीखरीदारी
    0.48
    Activations Density 0.003%

    No Known Activations