© 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. 40020
    Prev
    Next
    INDEX
    Explanations

    years

    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
     years
    -1.59
     Years
    -1.23
    years
    -1.21
     YEARS
    -1.16
    Years
    -1.13
     jaren
    -1.09
     Jahre
    -1.06
    YEARS
    -1.06
     años
    -0.99
    Jahre
    -0.92
    POSITIVE LOGITS
     Wallflower
    0.54
     Buddhism
    0.52
     Vicksburg
    0.52
     Tacitus
    0.50
    LocalizedString
    0.49
     Herodotus
    0.49
    HostException
    0.49
     Stonehenge
    0.49
     Jericho
    0.48
     commutative
    0.47
    Activations Density 0.981%

    No Known Activations