© 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. 0-CLT-HP
    7. 40193
    Prev
    Next
    INDEX
    Explanations

    Brain or align

    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
     Brain
    -1.48
     BRAIN
    -0.91
    Brain
    -0.80
    brain
    -0.79
     intracranial
    -0.72
     Brains
    -0.67
     brains
    -0.66
     excepted
    -0.63
    PROBE
    -0.63
     degeneracy
    -0.62
    POSITIVE LOGITS
    Vidite
    0.59
    queryInterface
    0.52
     Automata
    0.50
    tmpl
    0.49
    Eloquent
    0.48
     transfieras
    0.46
     grand
    0.46
    ADELPHIA
    0.46
     Section
    0.46
     propOrder
    0.46
    Activations Density 0.803%

    No Known Activations