© 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. 96351
    Prev
    Next
    INDEX
    Explanations

    a

    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
     recent
    -0.67
     good
    -0.62
    MLLoader
    -0.60
    DockStyle
    -0.56
     model
    -0.55
     suitable
    -0.55
     unique
    -0.54
     bus
    -0.54
     middle
    -0.54
     well
    -0.54
    POSITIVE LOGITS
     flesta
    0.66
     ifrån
    0.62
     pareti
    0.59
     copertura
    0.59
     colère
    0.58
     parete
    0.58
     termica
    0.58
     frequenza
    0.57
     låg
    0.57
     laterales
    0.56
    Activations Density 0.002%

    No Known Activations