© 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. 5-CLT-HP
    4. 94464
    Prev
    Next
    INDEX
    Explanations

    time adverbs

    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
    المكان
    -0.67
    expandindo
    -0.59
     made
    -0.59
    TOBER
    -0.57
    veden
    -0.57
     dubbed
    -0.56
    ÓW
    -0.55
    brido
    -0.55
     nicknamed
    -0.54
     inspired
    -0.54
    POSITIVE LOGITS
     and
    0.99
    .
    0.82
    ,
    0.77
    ;
    0.74
     but
    0.74
     as
    0.57
     <<<<<<<<<<<<<<
    0.54
     artificiales
    0.54
    and
    0.53
     --
    0.52
    Activations Density 0.001%

    No Known Activations