© 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. 4-CLT-HP
    7. 1204
    Prev
    Next
    INDEX
    Explanations

    different methods and approaches

    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
    <eos>
    -0.81
     klient
    -0.56
    σμα
    -0.53
     klienta
    -0.52
    Needs
    -0.52
    Has
    -0.50
    crí
    -0.49
    App
    -0.48
     fournisseurs
    -0.46
     frukt
    -0.46
    POSITIVE LOGITS
     competed
    0.79
     competing
    0.76
     simultaneously
    0.70
     compete
    0.67
     were
    0.67
     simultaneous
    0.66
     differing
    0.62
     identical
    0.62
     collided
    0.61
     wako
    0.61
    Activations Density 0.017%

    No Known Activations