© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40172
    Prev
    Next
    INDEX
    Explanations

    sky

    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
     sky
    -2.45
     Sky
    -1.92
    sky
    -1.86
    Sky
    -1.84
     skies
    -1.76
     SKY
    -1.63
    SKY
    -1.52
     heavens
    -1.28
     skys
    -1.27
     Skies
    -1.24
    POSITIVE LOGITS
    Contours
    0.57
    FXMLLoader
    0.49
    Տես
    0.47
    rshire
    0.44
    Хьажоргаш
    0.43
    aktor
    0.42
    Morfologia
    0.42
    @[+][
    0.41
    Descriptors
    0.41
    way
    0.40
    Activations Density 0.546%

    No Known Activations