© 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. 4-CLT-HP
    7. 104
    Prev
    Next
    INDEX
    Explanations

    limitations

    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
    ArgumentParser
    -0.60
     Limiting
    -0.59
     épais
    -0.58
    expandindo
    -0.57
    abestanden
    -0.57
     mourut
    -0.56
     limiting
    -0.56
     feroit
    -0.55
     @"/
    -0.54
     سكانية
    -0.54
    POSITIVE LOGITS
     ability
    0.92
     right
    0.74
     freedom
    0.72
     range
    0.70
     options
    0.66
     abilities
    0.65
    Right
    0.61
     незавершена
    0.59
     access
    0.59
     rights
    0.59
    Activations Density 0.004%

    No Known Activations