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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45294
    Prev
    Next
    INDEX
    Explanations

    protein

    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
     protein
    -0.84
     Protein
    -0.60
    thenReturn
    -0.58
     élevés
    -0.50
    Protein
    -0.47
    ември
    -0.47
     elevados
    -0.47
     препратки
    -0.47
    šanai
    -0.47
     ennemis
    -0.46
    POSITIVE LOGITS
    kháu
    0.72
     houſe
    0.62
    Xaml
    0.60
     superposition
    0.60
     vPvB
    0.60
     fractionation
    0.57
     doubtnut
    0.56
     perist
    0.56
    taxis
    0.56
     unification
    0.56
    Activations Density 0.300%

    No Known Activations