© 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. 94517
    Prev
    Next
    INDEX
    Explanations

    world, travel, global events

    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
     myſelf
    -1.02
     pleaſure
    -0.96
     Efq
    -0.93
     Majefty
    -0.88
     Houſe
    -0.88
     reaſon
    -0.86
     itſelf
    -0.85
     Reſ
    -0.84
     purpoſe
    -0.83
     themſelves
    -0.82
    POSITIVE LOGITS
    '
    0.66
    ’
    0.60
    ;
    0.58
    :
    0.54
    .
    0.54
     حاضر
    0.49
    ,
    0.48
    ans
    0.48
    ly
    0.48
    mybatisplus
    0.48
    Activations Density 0.057%

    No Known Activations