© 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. 12358
    Prev
    Next
    INDEX
    Explanations

    speed

    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
    Speed
    -0.90
     Speed
    -0.81
     speed
    -0.79
    SPEED
    -0.64
     SPEED
    -0.63
    speed
    -0.59
    peed
    -0.54
     speeds
    -0.50
     speeding
    -0.49
     speedy
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.99
     myſelf
    0.96
     itſelf
    0.95
     pleaſure
    0.87
     ―――――
    0.85
     purpoſe
    0.84
     tfsi
    0.84
     Eſ
    0.84
     raiſ
    0.83
     unſ
    0.82
    Activations Density 0.029%

    No Known Activations