© 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. 92224
    Prev
    Next
    INDEX
    Explanations

    Physics/physiology/metacognitive

    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
    s
    -0.56
     Plains
    -0.53
     Sim
    -0.50
     Plain
    -0.48
    sue
    -0.47
    sit
    -0.47
    invisible
    -0.47
    sink
    -0.46
     Human
    -0.46
    Invisible
    -0.46
    POSITIVE LOGITS
     argint
    0.78
    ngdoc
    0.76
     Majefty
    0.75
     fufficient
    0.75
     Anſ
    0.73
    abestanden
    0.71
     poffible
    0.71
     raiſ
    0.71
    Geplaatst
    0.70
     preſ
    0.70
    Activations Density 0.038%

    No Known Activations