© 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. 0-CLT-HP
    4. 45335
    Prev
    Next
    INDEX
    Explanations

    atom

    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
    中
    -0.55
    ordered
    -0.52
    D
    -0.50
    ish
    -0.50
    copy
    -0.50
    we
    -0.50
    ith
    -0.47
    -
    -0.47
    let
    -0.47
    ,
    -0.46
    POSITIVE LOGITS
     تضيفلها
    1.16
     myſelf
    1.13
    脚注の使い方
    1.10
    TargetException
    1.09
    ^(@)
    1.08
     itſelf
    1.05
    ]--;
    1.02
    )");
    
    1.02
    %");
    1.01
    oa̍t
    0.98
    Activations Density 0.738%

    No Known Activations