© 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. 0-CLT-HP
    7. 95271
    Prev
    Next
    INDEX
    Explanations

    banning or (im)balance

    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
     Balance
    -1.00
     balancing
    -0.97
    balance
    -0.88
     Balancing
    -0.86
     balance
    -0.85
    Balance
    -0.84
     Bal
    -0.83
     bal
    -0.82
     unbalanced
    -0.81
     balanced
    -0.81
    POSITIVE LOGITS
     samarbeid
    0.66
     rafraî
    0.66
     vectorielles
    0.65
     prochaines
    0.63
     réunis
    0.63
    
    0.61
    ″]
    0.61
     vérit
    0.60
     télécharge
    0.60
     préfé
    0.59
    Activations Density 0.541%

    No Known Activations