© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 97878
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    yntaxException
    -0.68
     ligiloj
    -0.65
    indd
    -0.60
    Пусть
    -0.60
    Géographie
    -0.59
    ModelAdmin
    -0.58
    )))
    
    -0.56
    )));
    
    -0.55
    ')));
    -0.55
    ']));
    -0.54
    POSITIVE LOGITS
     escalating
    0.55
    出版年
    0.49
     rapidly
    0.48
    ">//
    0.47
     continued
    0.47
     heightened
    0.47
     intensi
    0.47
     the
    0.46
     Russia
    0.46
    GraphicsUnit
    0.46
    Activations Density 0.001%

    No Known Activations