© 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. 15201
    Prev
    Next
    INDEX
    Explanations

    legal/financial texts

    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
     समीक्षक
    -0.53
     eint
    -0.52
    timeter
    -0.51
    뀜
    -0.50
     kemarin
    -0.47
    frutar
    -0.45
     génération
    -0.45
    ="@+
    -0.45
    onation
    -0.45
    becken
    -0.44
    POSITIVE LOGITS
     initComponents
    0.81
    reportWebVitals
    0.74
    WriteBarrier
    0.66
     MainAxisSize
    0.59
    Hentet
    0.58
    BeginContext
    0.57
    +#+#
    0.57
     stiffer
    0.57
     jaundice
    0.56
     kasarigan
    0.56
    Activations Density 0.015%

    No Known Activations