© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14267
    Prev
    Next
    INDEX
    Explanations

    truly

    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
     nôtre
    -0.63
     automatiques
    -0.59
     noires
    -0.58
     الحره
    -0.57
     détruit
    -0.54
     démocratie
    -0.54
     sportivo
    -0.53
     représenter
    -0.52
     fallu
    -0.51
    بوابة
    -0.50
    POSITIVE LOGITS
    حوالہ
    0.65
    VersionUID
    0.59
    chers
    0.57
    cher
    0.55
    ze
    0.52
    ting
    0.52
    doo
    0.52
    chery
    0.51
    UpdateUser
    0.51
    zole
    0.51
    Activations Density 0.017%

    No Known Activations