© 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. 92021
    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
    -1.18
     speed
    -1.15
    Speed
    -1.05
     SPEED
    -1.05
    speed
    -0.99
     Speeds
    -0.96
    peed
    -0.94
     speeds
    -0.91
    SPEED
    -0.90
     amarillas
    -0.88
    POSITIVE LOGITS
    ing
    0.77
    ed
    0.75
    y
    0.70
    iest
    0.65
    ized
    0.63
    ised
    0.63
    s
    0.59
    ier
    0.59
    ened
    0.55
    ily
    0.54
    Activations Density 0.090%

    No Known Activations