© 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. 973
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    ↵
    -1.52
    ↵↵
    -1.23
    ↵↵↵
    -0.89
     a
    -0.88
     the
    -0.85
     in
    -0.84
     all
    -0.82
     n
    -0.81
     la
    -0.81
     or
    -0.81
    POSITIVE LOGITS
     itſelf
    1.24
     varandra
    1.18
     avoient
    1.17
     Monfieur
    1.13
     étoient
    1.10
     myſelf
    1.09
     iſt
    1.05
     Jefus
    1.04
     Theſe
    1.04
     ainfi
    1.03
    Activations Density 2.213%

    No Known Activations