© 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. 93730
    Prev
    Next
    INDEX
    Explanations

    quench

    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
     quench
    -0.71
     recreate
    -0.63
     purge
    -0.62
    kus
    -0.56
     curation
    -0.53
    vive
    -0.52
     provoke
    -0.52
    aure
    -0.52
     recite
    -0.50
     mandate
    -0.50
    POSITIVE LOGITS
     myſelf
    0.99
     itſelf
    0.95
     themſelves
    0.90
     poffe
    0.89
     himſelf
    0.85
     ſeveral
    0.84
     ſtate
    0.81
     neceffary
    0.80
     raiſ
    0.79
     fevere
    0.79
    Activations Density 0.046%

    No Known Activations