© 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. 94568
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical "up to" phrases

    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
    )";
    
    -0.85
    RenderAtEndOf
    -0.75
     بيها
    -0.75
    ^(@)
    -0.73
    ніципа
    -0.72
    inerja
    -0.72
    })`
    -0.71
    }")
    
    -0.69
    <?
    -0.69
    )‏
    -0.66
    POSITIVE LOGITS
    MockMvc
    0.50
     
    0.46
     åt
    0.41
    Personensuche
    0.40
     or
    0.40
     büy
    0.40
     eighty
    0.40
     ninety
    0.39
     nakalista
    0.38
     as
    0.38
    Activations Density 0.001%

    No Known Activations