© 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. 94176
    Prev
    Next
    INDEX
    Explanations

    Problems or issues

    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
     cepillo
    -0.51
    движи
    -0.51
     arată
    -0.51
     pulso
    -0.50
    ived
    -0.50
     commerciali
    -0.50
     breach
    -0.50
     transfieras
    -0.49
    RUnlock
    -0.49
     fracaso
    -0.49
    POSITIVE LOGITS
     loading
    0.77
     running
    0.72
     importing
    0.72
     opening
    0.68
     Loading
    0.65
    httphttps
    0.63
    URLException
    0.60
     Importing
    0.60
     uploading
    0.59
     Opening
    0.57
    Activations Density 0.034%

    No Known Activations