© 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. 43556
    Prev
    Next
    INDEX
    Explanations

    hectares

    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
    -1.57
     purpoſe
    -1.48
     itſelf
    -1.43
     Monfieur
    -1.41
     Shakspeare
    -1.40
     Majefty
    -1.39
     Jefus
    -1.38
     Efq
    -1.36
     pleaſure
    -1.36
     Anſ
    -1.34
    POSITIVE LOGITS
     (
    0.72
     in
    0.69
     Bre
    0.68
     or
    0.68
     Her
    0.66
     for
    0.64
     Or
    0.64
     plus
    0.64
     pro
    0.63
     er
    0.62
    Activations Density 1.579%

    No Known Activations