© 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. 111
    Prev
    Next
    INDEX
    Explanations

    Code/Documentation Snippets

    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
     vendus
    -0.51
     fermés
    -0.50
     quelcon
    -0.47
    PackageManager
    -0.47
     marquées
    -0.47
    ++.
    -0.47
     déchir
    -0.46
     preocupes
    -0.45
     oscuros
    -0.45
     préc
    -0.44
    POSITIVE LOGITS
     par
    0.63
     staff
    0.63
     justice
    0.63
     waste
    0.61
     sal
    0.60
    abara
    0.59
     pinulongan
    0.59
     fire
    0.59
     shooting
    0.59
     user
    0.58
    Activations Density 0.000%

    No Known Activations