© 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. 5-CLT-HP
    7. 2516
    Prev
    Next
    INDEX
    Explanations

    operating system versions

    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
     Majefty
    -1.05
     Diſ
    -1.00
     pleaſure
    -0.98
     purpoſe
    -0.96
     Reſ
    -0.95
     ſtate
    -0.95
     ſever
    -0.93
     Anſ
    -0.92
     greateſt
    -0.92
     myſelf
    -0.91
    POSITIVE LOGITS
    ce
    0.55
    cite
    0.46
    CE
    0.39
    ci
    0.38
     khảo
    0.37
     m
    0.37
     c
    0.36
     Spicer
    0.36
    say
    0.36
     b
    0.35
    Activations Density 0.002%

    No Known Activations