© 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. 0-CLT-HP
    7. 94339
    Prev
    Next
    INDEX
    Explanations

    duplicate

    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
     duplication
    -0.74
     duplicated
    -0.71
     dup
    -0.59
     duplicates
    -0.55
     doublet
    -0.54
    GEBURTSDATUM
    -0.53
    rachtet
    -0.48
    ChildIndex
    -0.48
     ironing
    -0.47
    herzog
    -0.47
    POSITIVE LOGITS
    s
    1.60
    sers
    0.79
    ی
    0.79
    sach
    0.77
    sides
    0.77
    sak
    0.72
    sted
    0.72
    spe
    0.71
    ships
    0.71
    ship
    0.71
    Activations Density 0.228%

    No Known Activations