© 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. 92802
    Prev
    Next
    INDEX
    Explanations

    Washing/cleaning

    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
    Geplaatst
    -0.51
    ertos
    -0.47
    stdafx
    -0.44
    MigrationBuilder
    -0.42
    ագ
    -0.42
     də
    -0.42
    Ik
    -0.41
    StoreMessageInfo
    -0.41
    Up
    -0.41
     aange
    -0.41
    POSITIVE LOGITS
     out
    0.82
     away
    0.79
     oprot
    0.71
    PreferredItem
    0.68
     surla
    0.68
    ChildScrollView
    0.66
     clean
    0.65
     it
    0.62
    HOUT
    0.62
    out
    0.61
    Activations Density 0.000%

    No Known Activations