© 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. 4-CLT-HP
    4. 2394
    Prev
    Next
    INDEX
    Explanations

    age

    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
     nakalista
    -0.78
     defStyle
    -0.77
    MessageOf
    -0.74
     ExecuteAsync
    -0.73
    httphttps
    -0.72
    forChild
    -0.71
     الحره
    -0.71
    новништво
    -0.70
     betweenstory
    -0.70
     GenerationType
    -0.69
    POSITIVE LOGITS
     who
    0.45
     in
    0.41
     repres
    0.41
     represented
    0.40
    [
    0.36
     representa
    0.36
    compar
    0.36
    isce
    0.35
     elsewhere
    0.34
     pisau
    0.34
    Activations Density 0.003%

    No Known Activations