© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92450
    Prev
    Next
    INDEX
    Explanations

    Adjutant

    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
     itſelf
    -1.70
     myſelf
    -1.66
     Monfieur
    -1.56
     raiſ
    -1.53
     pleaſure
    -1.48
     Theſe
    -1.45
     ―――――
    -1.43
     purpoſe
    -1.41
     uſed
    -1.40
     Efq
    -1.38
    POSITIVE LOGITS
     r
    0.76
     Sta
    0.72
     der
    0.70
     Ar
    0.68
     ar
    0.66
     
    0.66
     R
    0.66
     d
    0.65
     e
    0.65
     of
    0.65
    Activations Density 0.149%

    No Known Activations