© 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. 4-CLT-HP
    7. 373
    Prev
    Next
    INDEX
    Explanations

    date/location prepositions

    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
     kasarigan
    -0.92
     שוליים
    -0.80
    Personendaten
    -0.78
    addCriterion
    -0.75
     himo
    -0.74
     autorytatywna
    -0.72
    awaiter
    -0.71
     ModelExpression
    -0.70
    +:+
    -0.69
    AsUp
    -0.69
    POSITIVE LOGITS
    béco
    0.49
    aus
    0.43
     selamat
    0.42
     واق
    0.41
    CHOS
    0.40
    script
    0.39
    lion
    0.38
     style
    0.38
    ссо
    0.38
     剪
    0.37
    Activations Density 0.004%

    No Known Activations