© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2053
    Prev
    Next
    INDEX
    Explanations

    include

    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
     думаете
    -0.54
    ไว้
    -0.53
    not
    -0.50
    exactly
    -0.48
    WithString
    -0.47
     exactly
    -0.47
    FAST
    -0.47
     Mikael
    -0.46
    publique
    -0.45
     vasta
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.63
    __((
    0.59
    ArrowToggle
    0.57
    хьтан
    0.57
     VIDEOTAPE
    0.57
    лябин
    0.55
    例句
    0.55
    yntaxException
    0.54
    TintMode
    0.54
    bcryptjs
    0.53
    Activations Density 0.004%

    No Known Activations