© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13522
    Prev
    Next
    INDEX
    Explanations

    quality

    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
    Quality
    -0.86
     quality
    -0.86
     kwaliteit
    -0.86
    quality
    -0.85
     CreateTagHelper
    -0.84
     qualidade
    -0.82
     Quality
    -0.80
     calidad
    -0.79
    QUALITY
    -0.77
     qualità
    -0.76
    POSITIVE LOGITS
     features
    0.49
     Lip
    0.47
     Pneum
    0.44
     solvents
    0.43
     Se
    0.43
     cues
    0.43
    clue
    0.42
     and
    0.41
     пере
    0.41
    morgan
    0.41
    Activations Density 0.036%

    No Known Activations