© 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. 93861
    Prev
    Next
    INDEX
    Explanations

    legal and financial documents

    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
    stdc
    -0.74
    ClientRect
    -0.70
    Manbalar
    -0.69
    migrationBuilder
    -0.68
     становника
    -0.65
    PROLOG
    -0.64
    StoryboardSegue
    -0.64
    aarrggbb
    -0.63
    Revenir
    -0.62
    +#+
    -0.61
    POSITIVE LOGITS
    i
    1.14
    s
    0.95
    a
    0.89
    o
    0.89
    e
    0.89
    er
    0.86
    y
    0.81
     alimentaires
    0.67
     financières
    0.63
    t
    0.62
    Activations Density 0.053%

    No Known Activations