© 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. 42339
    Prev
    Next
    INDEX
    Explanations

    programming development

    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
     pleaſure
    -0.89
     libraries
    -0.89
     Majefty
    -0.82
    ſelf
    -0.80
     ſtate
    -0.80
    Datuak
    -0.79
     iſt
    -0.78
     Jefus
    -0.77
    RectangleBorder
    -0.77
     '\\;'
    -0.76
    POSITIVE LOGITS
     sp
    0.50
     off
    0.50
     end
    0.48
     up
    0.47
     on
    0.47
     in
    0.46
     now
    0.46
     Now
    0.45
     let
    0.44
    ESTER
    0.43
    Activations Density 0.098%

    No Known Activations