© 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. 5-CLT-HP
    7. 98189
    Prev
    Next
    INDEX
    Explanations

    repairing

    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
     Bewegungs
    -0.50
     penge
    -0.47
    exercise
    -0.45
     reinstall
    -0.44
     reinstalling
    -0.43
     regaining
    -0.43
     Restoration
    -0.42
    recovered
    -0.42
    tować
    -0.41
     exercise
    -0.41
    POSITIVE LOGITS
     divides
    0.78
     divide
    0.74
     MainAxisSize
    0.72
     divisions
    0.68
     Divide
    0.67
     simplifié
    0.66
    complexContent
    0.62
    ]--;
    0.61
    GEBURTSDATUM
    0.61
    divide
    0.60
    Activations Density 0.001%

    No Known Activations