© 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. 5-CLT-HP
    7. 2870
    Prev
    Next
    INDEX
    Explanations

    time

    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
    gwt
    -0.49
    rungsseite
    -0.46
    eniem
    -0.44
     years
    -0.43
    くると
    -0.42
    multirow
    -0.42
     */
    -0.42
    existent
    -0.42
     legacies
    -0.41
     exist
    -0.41
    POSITIVE LOGITS
    fjspx
    0.89
    sizeCache
    0.84
     nahilalakip
    0.83
     ComVisible
    0.66
    záll
    0.63
    NameInMap
    0.63
    TintMode
    0.62
    qtype
    0.57
     ApiException
    0.56
     للاسماء
    0.56
    Activations Density 0.001%

    No Known Activations