© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 850
    Prev
    Next
    INDEX
    Explanations

    IL

    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
     reason
    -0.51
    ","");
    -0.50
    RoutingModule
    -0.49
    createServer
    -0.47
     EdgeInsets
    -0.47
    RefNanny
    -0.46
    codings
    -0.46
     geng
    -0.45
     pinulongan
    -0.45
    errar
    -0.45
    POSITIVE LOGITS
    CodedInputStream
    0.64
    StoryboardSegue
    0.60
     Backbone
    0.59
    batore
    0.56
    Advocate
    0.55
    tzmann
    0.54
     disambiguazione
    0.54
    Кла
    0.53
    ishly
    0.52
     menar
    0.52
    Activations Density 0.003%

    No Known Activations