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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2072
    Prev
    Next
    INDEX
    Explanations

    be

    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
     is
    -0.42
    Originally
    -0.33
    def
    -0.32
    an
    -0.32
    也非常
    -0.32
     oldukça
    -0.30
     kanton
    -0.29
    Conclusion
    -0.27
    </u>
    -0.27
     also
    -0.26
    POSITIVE LOGITS
    IntoConstraints
    1.16
     Efq
    1.13
     myſelf
    1.13
     CreateTagHelper
    1.12
     itſelf
    1.10
     pleaſure
    1.10
     purpoſe
    1.05
     neceff
    1.03
    ſelves
    1.02
     themſelves
    1.02
    Activations Density 0.025%

    No Known Activations