Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74347
    Prev
    Next
    INDEX
    Explanations

    amino acids

    np_max-act-logits · 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
     Antigen
    -0.84
     Cellulose
    -0.81
    elemField
    -0.73
     Epile
    -0.72
    cellulose
    -0.71
     Oxide
    -0.70
     Epilepsy
    -0.69
     financières
    -0.69
    ollectionView
    -0.69
    Calcium
    -0.68
    POSITIVE LOGITS
     L
    0.52
     a
    0.47
    Held
    0.44
     amino
    0.43
    L
    0.43
    ății
    0.38
    rokken
    0.38
     Held
    0.38
     LR
    0.38
     l
    0.38
    Activations Density 0.002%

    No Known Activations