© 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. 91629
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings

    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
    -0.68
     estekak
    -0.57
     betweenstory
    -0.57
    IntoConstraints
    -0.56
    orianCalendar
    -0.56
     <<<<<<<<<<<<<<
    -0.54
     Reconnaissance
    -0.54
    AnchorTagHelper
    -0.54
     Appellants
    -0.53
    DoubleQuotes
    -0.53
    POSITIVE LOGITS
     disambiguazione
    0.53
     OnInit
    0.52
    lias
    0.51
     دسته
    0.49
    ✨:
    0.49
    mies
    0.48
    mie
    0.48
    mybatisplus
    0.47
    dő
    0.47
    skins
    0.47
    Activations Density 0.000%

    No Known Activations