© 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. 1-CLT-HP
    7. 488
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     surla
    -0.87
     disambiguazione
    -0.83
     jScrollPane
    -0.82
    
    -0.70
    orteur
    -0.70
     TextInputType
    -0.69
    تقاوى
    -0.68
    蚪
    -0.68
     utafitiHapana
    -0.68
     Exactos
    -0.67
    POSITIVE LOGITS
     basis
    0.48
     Basis
    0.45
     bid
    0.40
    bindParam
    0.40
    k
    0.38
    VELAND
    0.38
    basis
    0.36
    pr
    0.36
    Basis
    0.36
    DataPropertyName
    0.36
    Activations Density 0.039%

    No Known Activations