© 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. 94874
    Prev
    Next
    INDEX
    Explanations

    computation and simulations

    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
    hésite
    -0.88
     computation
    -0.84
     Computation
    -0.77
     brancas
    -0.75
     écout
    -0.72
    Computation
    -0.71
     pleins
    -0.71
    explique
    -0.68
     simulates
    -0.67
     répondit
    -0.66
    POSITIVE LOGITS
    ReusableCell
    0.61
     contract
    0.61
    ('|
    0.59
     mark
    0.55
     team
    0.52
     co
    0.50
     party
    0.49
     '
    0.49
     detail
    0.49
     parties
    0.49
    Activations Density 0.103%

    No Known Activations