© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76047
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
    tagHelperRunner
    -0.89
     nahilalakip
    -0.75
     protoimpl
    -0.69
     typelib
    -0.66
    IonicModule
    -0.65
     ModelExpression
    -0.62
    ValueStyle
    -0.60
     Sixth
    -0.57
    writeFieldEnd
    -0.57
    FunctionFlags
    -0.55
    POSITIVE LOGITS
     polvere
    0.50
     võimal
    0.47
     commerciales
    0.46
    wpi
    0.46
     Италијани
    0.45
     morire
    0.45
    athione
    0.43
     trecut
    0.43
    Alpes
    0.43
    NECTION
    0.42
    Activations Density 0.000%

    No Known Activations