© 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. 1-CLT-HP
    7. 10180
    Prev
    Next
    INDEX
    Explanations

    as

    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
    them
    -0.52
    ه‌اند
    -0.51
     entweder
    -0.49
     addirittura
    -0.49
     intérieure
    -0.48
    broek
    -0.48
     habiendo
    -0.48
     kuitenkin
    -0.47
     यदि
    -0.47
     Either
    -0.46
    POSITIVE LOGITS
     poffible
    0.63
    (!__
    0.63
    peño
    0.60
    PerformLayout
    0.60
    VideoCapture
    0.57
    protoc
    0.55
    getChildAt
    0.54
    AndroidJUnit
    0.53
    ]--;
    0.52
     rumors
    0.52
    Activations Density 0.465%

    No Known Activations