© 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. 0-CLT-HP
    7. 93339
    Prev
    Next
    INDEX
    Explanations

    scenario

    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
     scenario
    -1.06
     scenarios
    -0.80
    scenario
    -0.78
     Scenario
    -0.77
     scénario
    -0.75
     outcome
    -0.70
    ########.
    -0.68
     possibility
    -0.66
    Scenario
    -0.66
     Scenarios
    -0.60
    POSITIVE LOGITS
    RectangleBorder
    0.63
    errHandler
    0.59
    ApplicationTests
    0.55
    dif
    0.53
     adjusting
    0.52
     offrire
    0.52
    cjach
    0.51
     growing
    0.50
     poveznice
    0.48
    randomUUID
    0.48
    Activations Density 0.063%

    No Known Activations