© 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. 2490
    Prev
    Next
    INDEX
    Explanations

    question words

    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
     "]";
    -0.54
    });*/
    -0.54
    ubehör
    -0.53
    Took
    -0.48
    }})
    -0.47
    ).)
    -0.46
     disponibilités
    -0.45
     Kazim
    -0.45
    AZA
    -0.45
     inkl
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.71
     تضيفلها
    0.64
     vertes
    0.64
    
    0.62
    /**
    0.62
    CloseOperation
    0.60
     AssemblyVersion
    0.60
    extAlignment
    0.60
    SequentialGroup
    0.59
    +:+
    0.57
    Activations Density 0.004%

    No Known Activations