© 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. 3104
    Prev
    Next
    INDEX
    Explanations

    way

    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
    ")));
    
    -0.75
    }\]
    -0.63
    <bos>
    -0.63
     дописавши
    -0.59
    "/>
    
    -0.57
    `}
    -0.56
    GeoNames
    -0.56
    "]);
    
    -0.55
     RPC
    -0.54
    />";
    -0.54
    POSITIVE LOGITS
     ExecuteAsync
    0.55
     ComVisible
    0.48
     however
    0.46
    いずれ
    0.45
     NSCoder
    0.44
     normalidad
    0.44
     typically
    0.44
    adpleegd
    0.44
    AddHtmlAttribute
    0.43
    ,
    0.43
    Activations Density 0.034%

    No Known Activations