© 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. 19
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Réponses
    -0.84
    Sucesor
    -0.61
    webElementXpaths
    -0.60
    IANGLES
    -0.59
    RegressionTest
    -0.57
     ExecuteAsync
    -0.56
    piecze
    -0.56
     viewDidLoad
    -0.56
    parsedMessage
    -0.54
    ]")]
    -0.54
    POSITIVE LOGITS
     professionnels
    0.56
    ագրություններ
    0.55
     fallu
    0.52
    __*/
    0.51
     professionisti
    0.50
     كومونز
    0.49
    Erreferentziak
    0.49
     layanan
    0.48
     experts
    0.47
     libraries
    0.47
    Activations Density 0.000%

    No Known Activations