© 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. 5-CLT-HP
    7. 94188
    Prev
    Next
    INDEX
    Explanations

    tutto

    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
     mxArray
    -0.62
     pulumi
    -0.52
    ‍♀️
    -0.46
     disambiguazione
    -0.46
     '').
    -0.45
    )$_
    -0.45
    fscanf
    -0.45
    ients
    -0.43
    ...")
    -0.43
    loe
    -0.43
    POSITIVE LOGITS
     among
    0.78
    among
    0.74
     مشين
    0.70
    PageRoute
    0.68
     NSCoder
    0.67
    MLLoader
    0.65
     exemplaires
    0.64
     amongst
    0.63
     producteurs
    0.63
     inoxydable
    0.63
    Activations Density 0.002%

    No Known Activations