© 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. 10149
    Prev
    Next
    INDEX
    Explanations

    excellent

    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
     cucchiaio
    -0.54
    onOptions
    -0.53
    Šaltiniai
    -0.51
     financières
    -0.50
     cucchia
    -0.48
    argli
    -0.47
     enfance
    -0.46
    lent
    -0.46
     asciug
    -0.46
     ویکی‌پدیا
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    0.63
    Saharan
    0.62
    Diweddarwch
    0.60
     tropic
    0.58
     sophistic
    0.57
    UnusedPrivate
    0.56
    TypedDataSet
    0.56
    ContentAsync
    0.56
    Ideally
    0.56
    rophes
    0.55
    Activations Density 0.004%

    No Known Activations