© 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. 1-CLT-HP
    7. 13427
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    الحياه
    -0.74
     fevere
    -0.73
     geox
    -0.72
     reaſon
    -0.72
     Efq
    -0.70
     Majefty
    -0.69
     Houſe
    -0.68
     houſe
    -0.67
    ^(@)
    -0.64
     vixion
    -0.64
    POSITIVE LOGITS
    /***/
    0.56
    transQ
    0.55
    -
    0.55
    новништво
    0.49
     back
    0.49
    complexType
    0.48
    y
    0.48
    SOURCE
    0.47
     --
    0.47
     conmigo
    0.46
    Activations Density 0.008%

    No Known Activations