© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38275
    Prev
    Next
    INDEX
    Explanations

    outdoor

    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
     lifestyles
    -1.09
     lifestyle
    -0.99
     outdoor
    -0.98
    Outdoor
    -0.98
    lifestyle
    -0.91
     myſelf
    -0.89
     Outdoor
    -0.86
    outdoor
    -0.84
     Lifestyle
    -0.80
     morire
    -0.80
    POSITIVE LOGITS
     ver
    0.48
     get
    0.48
    ecuted
    0.47
     emp
    0.47
    ary
    0.43
     상세
    0.43
     ens
    0.43
    nel
    0.42
    tium
    0.42
    itz
    0.42
    Activations Density 0.907%

    No Known Activations