© 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. 90814
    Prev
    Next
    INDEX
    Explanations

    company/code references

    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
     myſelf
    -1.28
     Monfieur
    -1.19
     Anſ
    -1.18
     themſelves
    -1.17
     Efq
    -1.16
     itſelf
    -1.14
     ſtate
    -1.13
     purpoſe
    -1.13
     Majefty
    -1.10
     ſeveral
    -1.10
    POSITIVE LOGITS
     
    0.64
     co
    0.62
     s
    0.59
     Co
    0.58
     “
    0.57
     I
    0.55
     "
    0.54
     ing
    0.54
     Re
    0.54
     No
    0.54
    Activations Density 0.127%

    No Known Activations