© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 15497
    Prev
    Next
    INDEX
    Explanations

    past-tense verbs

    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
    IntoConstraints
    -0.65
     AssemblyProduct
    -0.63
    Controllo
    -0.60
    jelaskan
    -0.56
    Viited
    -0.56
    umumkan
    -0.56
     réjou
    -0.53
     propOrder
    -0.53
     незавершена
    -0.53
    BeginContext
    -0.53
    POSITIVE LOGITS
     raiſ
    0.63
     ſtand
    0.55
    httphttps
    0.54
     myſelf
    0.53
     himſelf
    0.52
     kait
    0.51
     pleaſure
    0.51
     tranſ
    0.51
     ſta
    0.51
     Jefus
    0.51
    Activations Density 0.007%

    No Known Activations