© 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. 77725
    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
    DoubleQuotes
    -0.59
    发表于
    -0.58
    mobileqq
    -0.57
    PullParser
    -0.57
    zuli
    -0.56
     الحره
    -0.56
     venons
    -0.56
    nake
    -0.56
    Дереккөздер
    -0.56
    EndInit
    -0.55
    POSITIVE LOGITS
    Den
    0.50
    delwed
    0.45
     Den
    0.43
    UpdateCommand
    0.40
     كره
    0.40
     disarm
    0.39
     Denial
    0.38
    AdapterFactory
    0.37
     denial
    0.37
     sadar
    0.37
    Activations Density 0.000%

    No Known Activations