© 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. 20-CLT-HP
    7. 72031
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · 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
    NOPQRST
    -0.56
    ں
    -0.53
    IntoConstraints
    -0.52
    <![
    -0.52
    enação
    -0.51
     paws
    -0.51
    lyon
    -0.50
     bào
    -0.50
     sneezing
    -0.50
    Viitteet
    -0.49
    POSITIVE LOGITS
     كومونز
    0.75
     HasFactory
    0.73
    abestanden
    0.59
     resume
    0.57
     propOrder
    0.56
    Portale
    0.54
     ISNI
    0.53
     hold
    0.53
    Хьажоргаш
    0.52
    ագրություններ
    0.51
    Activations Density 0.000%

    No Known Activations