© 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. 1-CLT-HP
    7. 9066
    Prev
    Next
    INDEX
    Explanations

    Fi

    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
    rus
    -0.59
     rus
    -0.50
     ambao
    -0.42
     blessure
    -0.42
     batches
    -0.42
    rtz
    -0.41
    itás
    -0.40
    姆斯
    -0.40
    NOPQRST
    -0.39
     frescos
    -0.39
    POSITIVE LOGITS
    Tembelea
    0.75
     viewDidLoad
    0.71
    Xna
    0.68
     виправивши
    0.68
     utafitiHapana
    0.68
    mybatisplus
    0.66
    expandindo
    0.65
    ագրություններ
    0.64
    Filmographie
    0.64
     propOrder
    0.63
    Activations Density 0.041%

    No Known Activations