© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43657
    Prev
    Next
    INDEX
    Explanations

    decade

    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
     decade
    -1.16
     Majefty
    -1.14
    decade
    -1.13
    ContentAsync
    -1.07
     Basically
    -1.05
     Jefus
    -1.03
    basically
    -0.99
     Essentially
    -0.98
    ſelf
    -0.96
    Datuak
    -0.96
    POSITIVE LOGITS
     an
    0.77
     the
    0.75
     a
    0.74
     “
    0.67
     "
    0.60
     som
    0.53
    ,
    0.53
     walk
    0.52
     one
    0.52
     some
    0.52
    Activations Density 0.091%

    No Known Activations