© 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. 42674
    Prev
    Next
    INDEX
    Explanations

    nostalgia

    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
    lit
    -0.69
    lish
    -0.57
    mon
    -0.52
     arre
    -0.52
    ließ
    -0.51
     lit
    -0.50
    literature
    -0.48
    ence
    -0.47
    complexContent
    -0.47
    bir
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.82
    ity
    0.71
    ITY
    0.63
    photobucket
    0.63
    AnimationsModule
    0.63
    odotus
    0.62
     Pingback
    0.61
    ired
    0.60
    IMPORTED
    0.60
    addGap
    0.60
    Activations Density 0.048%

    No Known Activations