© 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. 0-CLT-HP
    7. 42559
    Prev
    Next
    INDEX
    Explanations

    magn

    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
    zig
    -0.64
     mes
    -0.52
     dia
    -0.52
    ings
    -0.50
     relations
    -0.48
    照
    -0.47
    mer
    -0.46
     diff
    -0.46
    manjaro
    -0.45
    lazione
    -0.44
    POSITIVE LOGITS
     définiti
    0.80
    IContainer
    0.77
     précie
    0.67
     Monfieur
    0.67
     financières
    0.63
    TypedDataSet
    0.62
     grève
    0.62
     condam
    0.61
     Afonso
    0.60
    ]='\
    0.60
    Activations Density 0.162%

    No Known Activations