© 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. 4-CLT-HP
    7. 4953
    Prev
    Next
    INDEX
    Explanations

    Continuation/Forwarding of information

    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
     films
    -0.48
    JoinColumn
    -0.46
    ]<<"
    -0.46
    辞典
    -0.46
    OLIS
    -0.46
    fycat
    -0.45
    MathML
    -0.44
    ceda
    -0.43
    rizona
    -0.43
    WebVitals
    -0.42
    POSITIVE LOGITS
    
    0.65
     незавершена
    0.56
     مشين
    0.56
     Wikimedijinoj
    0.55
    ValueStyle
    0.55
    AutoresizingMask
    0.54
    AxisAlignment
    0.54
     通販
    0.54
    saurus
    0.53
    chè
    0.52
    Activations Density 0.022%

    No Known Activations