© 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. 1-CLT-HP
    7. 10163
    Prev
    Next
    INDEX
    Explanations

    aesthetic

    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
     Aesthetic
    -1.40
     aesthetic
    -1.32
    Aesthetic
    -1.21
    aesthetic
    -1.18
     Aesthetics
    -1.07
     aesthetics
    -1.06
     estética
    -0.84
     esthétique
    -0.83
     estético
    -0.82
     эсте
    -0.77
    POSITIVE LOGITS
    ValueStyle
    0.76
     initComponents
    0.73
    CloseOperation
    0.66
     مرئيه
    0.65
     Normdatei
    0.63
    ally
    0.63
     Bourgoin
    0.63
     linkovi
    0.63
    Datuak
    0.60
    contentLoaded
    0.60
    Activations Density 0.008%

    No Known Activations