© 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. 10192
    Prev
    Next
    INDEX
    Explanations

    electrical circuits

    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
     kasarigan
    -0.95
     MainAxisSize
    -0.93
    InjectAttribute
    -0.83
     Macaulay
    -0.67
    enderror
    -0.66
     <=",
    -0.65
     IBOutlet
    -0.62
     Pamph
    -0.61
     Dalton
    -0.59
     Standardized
    -0.58
    POSITIVE LOGITS
     ích
    0.45
    HomeAsUpEnabled
    0.41
    bit
    0.41
    SOUNDBITE
    0.40
     cik
    0.40
    }*/
    0.39
    Bodies
    0.39
    撇
    0.39
     on
    0.38
    щадь
    0.38
    Activations Density 0.032%

    No Known Activations