© 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. 96404
    Prev
    Next
    INDEX
    Explanations

    scientific names

    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
     free
    -0.54
     staff
    -0.46
     presentation
    -0.45
     surrounding
    -0.41
     election
    -0.41
     trick
    -0.40
     above
    -0.40
     advance
    -0.40
     budget
    -0.40
     overnight
    -0.39
    POSITIVE LOGITS
    OPSIS
    0.67
    formis
    0.64
    galus
    0.63
    elemField
    0.60
     становника
    0.59
    SPATH
    0.57
     HasFactory
    0.57
    foria
    0.56
    tamol
    0.56
    ifolia
    0.55
    Activations Density 0.047%

    No Known Activations