© 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. 5495
    Prev
    Next
    INDEX
    Explanations

    boost

    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
    StreetMap
    -0.63
    ValueStyle
    -0.58
    Personendaten
    -0.54
    interopRequire
    -0.53
    énario
    -0.52
    %)$
    -0.51
    MessageTagHelper
    -0.51
     realise
    -0.50
     then
    -0.50
     bParam
    -0.50
    POSITIVE LOGITS
    <bos>
    0.69
    bewerken
    0.48
    IUrlHelper
    0.46
     EconPapers
    0.46
    ruptedException
    0.45
     referenties
    0.45
     ویکی‌آمباردا
    0.44
     parede
    0.43
    beto
    0.43
    contentLoaded
    0.43
    Activations Density 0.000%

    No Known Activations