© 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. 4-CLT-HP
    7. 2721
    Prev
    Next
    INDEX
    Explanations

    index

    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
     PSS
    -0.51
     Karriere
    -0.50
     PLL
    -0.50
     DSP
    -0.47
    ServiceModel
    -0.46
    avigation
    -0.46
     dealing
    -0.45
     Cambrian
    -0.45
     LIV
    -0.44
     unequiv
    -0.44
    POSITIVE LOGITS
    WebElementEntity
    0.70
    หวัด
    0.60
    MethodManager
    0.60
    XmlEnum
    0.59
    ########.
    0.58
     للاسماء
    0.57
     "..\..\
    0.57
     препратки
    0.57
    RegressionTest
    0.56
    MENAFN
    0.56
    Activations Density 0.006%

    No Known Activations