© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42192
    Prev
    Next
    INDEX
    Explanations

    Treasurer

    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
     Treasurer
    -1.16
     treasurer
    -1.12
    Treasurer
    -1.00
    UnusedPrivate
    -1.00
    AndEndTag
    -0.86
    TagMode
    -0.83
    LookAnd
    -0.82
    Composable
    -0.81
    StoryboardSegue
    -0.76
    fjspx
    -0.76
    POSITIVE LOGITS
    kjø
    0.43
     للاسماء
    0.42
    ize
    0.42
    Приятного
    0.39
    !("{}",
    0.39
     cooperative
    0.38
    TFT
    0.37
     disponibilités
    0.36
    modelBuilder
    0.36
    '])->
    0.36
    Activations Density 0.114%

    No Known Activations