© 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. 5-CLT-HP
    7. 92996
    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
     Or
    -0.61
    ↵
    -0.50
     OR
    -0.47
    anthene
    -0.45
     Of
    -0.44
     professional
    -0.43
    OrEqual
    -0.43
    fluence
    -0.41
    Or
    -0.41
    OrEqualTo
    -0.40
    POSITIVE LOGITS
    GraphicsUnit
    0.95
     الدولى
    0.84
     GenerationType
    0.84
     Monfieur
    0.80
     itſelf
    0.78
     nakalista
    0.77
     Jefus
    0.75
    enumii
    0.71
     Majefty
    0.70
     myſelf
    0.70
    Activations Density 0.005%

    No Known Activations