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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14547
    Prev
    Next
    INDEX
    Explanations

    Devices and time keeping

    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
     clock
    -1.05
     Clock
    -0.98
    Clock
    -0.82
     clocks
    -0.81
     CLOCK
    -0.80
    clock
    -0.78
     Clocks
    -0.71
    CLOCK
    -0.66
     clocked
    -0.52
     reloj
    -0.51
    POSITIVE LOGITS
     незавершена
    0.65
     Ceramby
    0.64
    enumi
    0.64
     subgoal
    0.63
    AddHtmlAttribute
    0.60
     internazionale
    0.57
     IBOutlet
    0.57
     betweenstory
    0.56
    AndEndTag
    0.56
     JAXBElement
    0.56
    Activations Density 0.008%

    No Known Activations