© 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. 4-CLT-HP
    7. 1055
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and codes

    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
     last
    -0.47
    kr
    -0.47
     ام
    -0.44
     of
    -0.43
    pha
    -0.41
     ngh
    -0.41
    lus
    -0.41
    hig
    -0.41
    mph
    -0.41
    imal
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    0.99
     itſelf
    0.97
     myſelf
    0.94
     Monfieur
    0.92
     pleaſure
    0.92
     NSCoder
    0.90
     themſelves
    0.82
     himſelf
    0.81
     Efq
    0.81
     purpoſe
    0.80
    Activations Density 0.387%

    No Known Activations