© 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. 732
    Prev
    Next
    INDEX
    Explanations

    Code/Markup

    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
    ...:
    -0.60
    </h2>
    -0.56
     sy
    -0.55
    ientôt
    -0.51
     bere
    -0.51
    #:
    -0.51
     forgot
    -0.50
    </h1>
    -0.50
    %:
    -0.49
     {}'.
    -0.47
    POSITIVE LOGITS
     démocr
    0.81
     supérieurs
    0.79
     supérieures
    0.77
     quelcon
    0.75
     nationaux
    0.73
    ValueStyle
    0.71
     réguli
    0.71
     traditionnels
    0.70
     verrez
    0.70
     feroit
    0.69
    Activations Density 0.030%

    No Known Activations