© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3051
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     who
    -0.69
    (
    -0.55
     this
    -0.54
     and
    -0.53
     these
    -0.49
     to
    -0.49
    ↵
    -0.48
     (
    -0.48
     have
    -0.48
     is
    -0.47
    POSITIVE LOGITS
    RegressionTest
    1.02
     surla
    1.02
     Wiktionnaire
    1.00
     resourceCulture
    0.97
    Geplaatst
    0.97
     nakalista
    0.93
    ]")]
    0.91
    rungsseite
    0.91
     betweenstory
    0.90
    rawDesc
    0.88
    Activations Density 0.000%

    No Known Activations