© 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. 5-CLT-HP
    7. 92466
    Prev
    Next
    INDEX
    Explanations

    Common words in varied texts

    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
    KommentareTeilen
    -0.70
     étoit
    -0.69
     auroit
    -0.62
     réglementation
    -0.61
     تضيفلها
    -0.60
    didSet
    -0.57
    BeginInit
    -0.56
     juridique
    -0.54
     jurídica
    -0.54
     mignon
    -0.54
    POSITIVE LOGITS
    first
    0.63
    WithIOException
    0.57
    apimachinery
    0.56
    uerst
    0.53
     اولین
    0.53
     first
    0.53
     utafitiHapana
    0.52
    First
    0.52
    ⓘ
    0.51
     Tuch
    0.49
    Activations Density 0.005%

    No Known Activations