© 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. 45343
    Prev
    Next
    INDEX
    Explanations

    scheduling

    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
     purpoſe
    -1.09
     pleaſure
    -1.05
     myſelf
    -1.02
     ſtate
    -1.01
     Anſ
    -1.00
     uſe
    -1.00
     Majefty
    -0.99
     ſever
    -0.98
     himſelf
    -0.97
     ſta
    -0.95
    POSITIVE LOGITS
    .
    0.52
    :
    0.47
     of
    0.46
    -
    0.46
     T
    0.46
     t
    0.45
     incomplète
    0.45
    UrlResolution
    0.45
     Brown
    0.44
     mit
    0.43
    Activations Density 0.238%

    No Known Activations