© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45378
    Prev
    Next
    INDEX
    Explanations

    assuming

    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
     assuming
    -1.11
    assuming
    -0.94
     leaving
    -0.93
     AssemblyCulture
    -0.91
     considerando
    -0.90
     returning
    -0.88
     adopting
    -0.85
     supporting
    -0.81
     pursuing
    -0.80
     Assuming
    -0.80
    POSITIVE LOGITS
     possession
    0.68
    ürtel
    0.64
    xion
    0.58
    нской
    0.54
    μβ
    0.53
    tto
    0.53
    teras
    0.51
     poss
    0.50
     Betten
    0.50
    oslav
    0.50
    Activations Density 0.344%

    No Known Activations