© 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. 9207
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
     Tuesday
    -1.05
     Monday
    -1.04
     Thursday
    -0.96
    Tuesday
    -0.93
     BoxFit
    -0.92
    Monday
    -0.90
     Sunday
    -0.90
     Wednesday
    -0.89
     Saturday
    -0.88
     Friday
    -0.85
    POSITIVE LOGITS
     Nite
    0.64
     night
    0.60
     nite
    0.58
     Night
    0.52
    ISupport
    0.50
    Night
    0.48
     NIGHT
    0.48
     maille
    0.44
     solaire
    0.43
    valt
    0.42
    Activations Density 0.050%

    No Known Activations