© 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. 42215
    Prev
    Next
    INDEX
    Explanations

    incomplete

    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
    gs
    -1.13
     outlet
    -1.04
     outlets
    -1.00
     Outlet
    -0.94
     incomplete
    -0.87
     Outlets
    -0.87
    outlet
    -0.81
     Incomplete
    -0.75
     Intention
    -0.72
     intention
    -0.70
    POSITIVE LOGITS
     façons
    0.51
    expandindo
    0.49
     BoxFit
    0.48
    ekš
    0.46
    ykjav
    0.44
     autorisé
    0.44
     DISC
    0.44
     crossorigin
    0.44
    kuuta
    0.43
    okości
    0.43
    Activations Density 0.070%

    No Known Activations