© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38994
    Prev
    Next
    INDEX
    Explanations

    to

    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
    To
    -1.31
     To
    -1.25
     TO
    -0.89
     to
    -0.70
    ly
    -0.66
    ToTop
    -0.60
     extérieures
    -0.57
     gerichtet
    -0.57
    ToPoint
    -0.57
     kepada
    -0.56
    POSITIVE LOGITS
     be
    0.95
     avoid
    0.94
     get
    0.91
     ensure
    0.91
    ilets
    0.91
     make
    0.90
     obtain
    0.87
     provide
    0.85
     learn
    0.84
     celebrate
    0.83
    Activations Density 0.216%

    No Known Activations