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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38992
    Prev
    Next
    INDEX
    Explanations

    bootstra

    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
    IntoConstraints
    -0.88
     élevées
    -0.85
     définiti
    -0.82
     AssemblyCulture
    -0.81
     démocr
    -0.78
     financières
    -0.78
     Paglinawan
    -0.75
     élevés
    -0.73
     européennes
    -0.73
     supérieurs
    -0.72
    POSITIVE LOGITS
    ness
    0.64
     Cla
    0.53
     lend
    0.51
    nom
    0.50
    night
    0.49
     Philipp
    0.49
     meet
    0.49
     PNP
    0.48
     n
    0.48
    nera
    0.47
    Activations Density 0.046%

    No Known Activations