© 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. 77737
    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
     незавершена
    -0.65
    Портал
    -0.57
    出版年
    -0.56
    AutoScaleMode
    -0.54
    PerformLayout
    -0.50
     Exactos
    -0.48
    ebus
    -0.47
    protos
    -0.47
    fonds
    -0.46
    خواه
    -0.46
    POSITIVE LOGITS
     PyLong
    0.52
     scro
    0.52
    Partici
    0.50
    kuuta
    0.49
    itarianism
    0.48
     autorytatywna
    0.47
     locate
    0.47
     eyelids
    0.47
    antula
    0.47
     loc
    0.47
    Activations Density 0.006%

    No Known Activations