© 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. 1965
    Prev
    Next
    INDEX
    Explanations

    v

    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
     v
    -1.00
     c
    -0.93
     m
    -0.91
     web
    -0.83
     p
    -0.81
     mouse
    -0.79
     rat
    -0.73
     Mouse
    -0.73
     a
    -0.72
     n
    -0.71
    POSITIVE LOGITS
     Majefty
    1.15
     Efq
    1.10
     myſelf
    1.10
     pleaſure
    1.07
     itſelf
    1.06
    ſelf
    1.05
     Eſ
    1.04
     Houſe
    1.02
     Jefus
    1.02
     Reſ
    1.02
    Activations Density 0.384%

    No Known Activations