© 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. 76171
    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
    RegressionTest
    -0.65
    RunAsync
    -0.64
    ">—
    -0.60
    Хьажоргаш
    -0.58
    PerformLayout
    -0.57
     Normdatei
    -0.57
    SerializedSize
    -0.55
    MENAFN
    -0.54
    XmlType
    -0.54
    Rujuakan
    -0.53
    POSITIVE LOGITS
     ModelExpression
    0.66
    İstinadlar
    0.63
    ScopeManager
    0.54
    Linki
    0.53
    utsches
    0.51
    Kjelder
    0.50
     atentos
    0.47
    Bibliograf
    0.45
    Men
    0.44
    ագրություններ
    0.44
    Activations Density 0.002%

    No Known Activations