© 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. 15556
    Prev
    Next
    INDEX
    Explanations

    by

    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
    </caption>
    -0.79
     EconPapers
    -0.77
     Pristupljeno
    -0.73
    OGND
    -0.72
    rawDesc
    -0.72
    رشف
    -0.69
    Hozzáférés
    -0.67
    parsedMessage
    -0.66
    SequentialGroup
    -0.65
    
    -0.64
    POSITIVE LOGITS
     fumée
    0.41
     mutu
    0.38
     five
    0.37
     bébés
    0.37
    se
    0.37
     rédu
    0.37
    atier
    0.37
     rayos
    0.36
     épais
    0.36
    ancang
    0.35
    Activations Density 0.027%

    No Known Activations