© 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. 20-CLT-HP
    7. 74544
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    Driven
    -0.63
     Driven
    -0.60
     fizer
    -0.60
    Written
    -0.55
    driven
    -0.55
     localize
    -0.54
    ventil
    -0.54
     learns
    -0.53
     sogni
    -0.53
     haft
    -0.52
    POSITIVE LOGITS
     attempted
    0.83
     kept
    0.82
     stepped
    0.82
     opened
    0.81
     returned
    0.81
     repaired
    0.79
     made
    0.79
     picked
    0.78
     clicked
    0.78
     passed
    0.77
    Activations Density 0.012%

    No Known Activations