© 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. 5920
    Prev
    Next
    INDEX
    Explanations

    marriage

    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
    rativa
    -0.51
     getSystem
    -0.50
    setContentView
    -0.47
    клопе
    -0.46
    ifax
    -0.46
     latter
    -0.45
     later
    -0.45
     fieldNum
    -0.44
     recensement
    -0.44
    Identyfik
    -0.44
    POSITIVE LOGITS
     كومونز
    0.69
    AddHtmlAttribute
    0.67
    __(/*!
    0.65
     يتيمه
    0.63
    anță
    0.61
     poveznice
    0.61
    сылкі
    0.60
    SourceChecksum
    0.59
    sizeCache
    0.59
    thâu
    0.57
    Activations Density 0.002%

    No Known Activations