© 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. 94996
    Prev
    Next
    INDEX
    Explanations

    formal/technical writing

    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
     rain
    -0.55
    rain
    -0.54
    rainy
    -0.54
     pola
    -0.52
     Rain
    -0.51
    diert
    -0.50
    下雨
    -0.49
    rains
    -0.48
     rained
    -0.47
     [*]
    -0.47
    POSITIVE LOGITS
     myſelf
    1.00
     itſelf
    0.95
    ſelf
    0.90
     Efq
    0.89
     themſelves
    0.88
     himſelf
    0.86
     uſed
    0.84
     ſhe
    0.84
     raiſ
    0.84
     ſta
    0.83
    Activations Density 0.300%

    No Known Activations