© 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. 1-CLT-HP
    7. 13485
    Prev
    Next
    INDEX
    Explanations

    insights

    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
     insights
    -0.82
     Insights
    -0.81
    Hochspringen
    -0.72
     avoient
    -0.70
     RIPRODUZIONE
    -0.69
     चीज़ों
    -0.67
    insights
    -0.66
    Insights
    -0.66
    alised
    -0.66
     Anſ
    -0.66
    POSITIVE LOGITS
    s
    0.55
     ret
    0.51
     reg
    0.50
    vermögen
    0.49
     interesar
    0.49
     F
    0.46
    rrggbb
    0.45
     re
    0.44
    akti
    0.43
     ministry
    0.43
    Activations Density 0.026%

    No Known Activations