© 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. 0-CLT-HP
    7. 40235
    Prev
    Next
    INDEX
    Explanations

    amber

    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
    active
    -0.97
     varandra
    -0.91
     stället
    -0.81
     bakgrund
    -0.77
     aktivitet
    -0.77
     Monfieur
    -0.77
     armée
    -0.75
     optique
    -0.74
    ttemberg
    -0.73
     Anſ
    -0.72
    POSITIVE LOGITS
    IsContent
    0.61
    ciu
    0.55
    .
    0.52
     Tre
    0.52
    ́s
    0.52
     hand
    0.51
     Sud
    0.51
     plan
    0.50
     design
    0.50
     subject
    0.50
    Activations Density 0.165%

    No Known Activations