© 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. 5-CLT-HP
    7. 92632
    Prev
    Next
    INDEX
    Explanations

    List of characters

    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
    bindingNavigator
    -0.47
    nien
    -0.46
    öll
    -0.45
     segn
    -0.45
    PMG
    -0.44
    läufer
    -0.43
     ngại
    -0.42
    culin
    -0.41
    Spi
    -0.41
    XIC
    -0.40
    POSITIVE LOGITS
    Legături
    0.69
    DoubleQuotes
    0.67
    errHandler
    0.65
     صوتيه
    0.61
    WriteTagHelper
    0.61
    XmlAccessType
    0.57
    GEBURTSDATUM
    0.57
    mybatisplus
    0.57
     AssemblyCompany
    0.57
    GIVEREF
    0.56
    Activations Density 0.011%

    No Known Activations