© 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. 5-CLT-HP
    7. 92132
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     kaynağından
    -0.65
     initComponents
    -0.63
    сылкі
    -0.62
    లాలు
    -0.59
     StatelessWidget
    -0.59
    ########.
    -0.59
     Normdatei
    -0.58
    וויק
    -0.57
     Walkover
    -0.57
    findpost
    -0.57
    POSITIVE LOGITS
     experiment
    0.56
     game
    0.54
     Experiment
    0.54
     metropolis
    0.50
    phonie
    0.48
     Empire
    0.48
     universal
    0.46
     Starling
    0.45
     Game
    0.45
     Encyclopedia
    0.45
    Activations Density 0.001%

    No Known Activations