© 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. 4-CLT-HP
    7. 3272
    Prev
    Next
    INDEX
    Explanations

    0

    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
     démocr
    -0.73
     épaules
    -0.71
    vedať
    -0.68
     genoux
    -0.67
    SuppressMessage
    -0.67
     oídos
    -0.66
    ScopeManager
    -0.65
     courants
    -0.65
     lumières
    -0.64
     mères
    -0.63
    POSITIVE LOGITS
     незавершена
    0.68
     виправивши
    0.51
     exec
    0.49
    WebElementEntity
    0.48
     Roskov
    0.47
    Diweddarwch
    0.47
    thâu
    0.47
     scru
    0.46
     congressional
    0.46
     universes
    0.46
    Activations Density 0.018%

    No Known Activations