© 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. 1-CLT-HP
    7. 11752
    Prev
    Next
    INDEX
    Explanations

    cache

    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
     cache
    -0.71
    cache
    -0.68
    Cache
    -0.63
    caching
    -0.63
     caching
    -0.63
    Caching
    -0.60
     Cache
    -0.55
     CACHE
    -0.54
    CACHE
    -0.53
     March
    -0.49
    POSITIVE LOGITS
     contextLoads
    0.63
     yyr
    0.61
     propOrder
    0.61
    ]--;
    0.60
    دانشنامهٔ
    0.60
    uire
    0.59
     jspb
    0.59
     المعيارى
    0.57
    ########.
    0.56
    krát
    0.56
    Activations Density 0.420%

    No Known Activations