© 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. 5513
    Prev
    Next
    INDEX
    Explanations

    tim

    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
    rungsseite
    -0.92
    onAttach
    -0.78
     refusing
    -0.71
     riders
    -0.70
     charging
    -0.69
    bootstrapcdn
    -0.69
     oblige
    -0.68
    ⓧ
    -0.68
     skier
    -0.68
     suspensions
    -0.67
    POSITIVE LOGITS
     fédé
    0.52
     stedet
    0.50
     stället
    0.49
    Hentet
    0.46
     prochaines
    0.45
     realistas
    0.44
     varandra
    0.44
     élas
    0.43
     quelcon
    0.43
     sièges
    0.43
    Activations Density 0.003%

    No Known Activations