© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    telling a story

    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
     كومونز
    -0.64
     /\.
    -0.63
     Signalez
    -0.62
     وتسجيلات
    -0.61
    arschijnlijk
    -0.61
    areth
    -0.60
     Allociné
    -0.59
    icrous
    -0.59
    ียญ
    -0.58
    simus
    -0.57
    POSITIVE LOGITS
     consultato
    0.71
    ymce
    0.52
     thống
    0.47
    VersionUID
    0.46
    ProgressHUD
    0.44
    #:
    0.44
     of
    0.41
    initComponents
    0.40
    ImageIO
    0.40
    
    0.40
    Activations Density 0.002%

    No Known Activations