© 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. 92164
    Prev
    Next
    INDEX
    Explanations

    Facebook

    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
     May
    -0.96
     O
    -0.81
     You
    -0.81
     L
    -0.70
     R
    -0.66
     U
    -0.65
     D
    -0.64
     August
    -0.63
     S
    -0.62
     E
    -0.62
    POSITIVE LOGITS
     myſelf
    1.12
     itſelf
    1.05
     Monfieur
    1.04
    ſelf
    0.97
     themſelves
    0.97
     Anſ
    0.97
     Theſe
    0.96
     himſelf
    0.95
     ſche
    0.94
     Diſ
    0.93
    Activations Density 0.083%

    No Known Activations