© 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. 0-CLT-HP
    7. 41284
    Prev
    Next
    INDEX
    Explanations

    Ge

    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
     watch
    -1.02
     Ge
    -0.92
     Watch
    -0.86
     ge
    -0.80
    watch
    -0.80
     (
    -0.71
    Watch
    -0.71
     
    -0.71
     WATCH
    -0.70
     I
    -0.67
    POSITIVE LOGITS
     myſelf
    1.36
     Monfieur
    1.36
     Efq
    1.35
     Houſe
    1.34
     Jefus
    1.32
     houſe
    1.30
     itſelf
    1.30
     Anſ
    1.29
     pleaſure
    1.27
     Eſ
    1.25
    Activations Density 1.982%

    No Known Activations