© 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. 1-CLT-HP
    4. 1041
    Prev
    Next
    INDEX
    Explanations

    ddle

    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
    ddle
    -0.94
     Efq
    -0.85
     whoſe
    -0.78
     myſelf
    -0.77
     themſelves
    -0.76
     becauſe
    -0.73
     Chriftian
    -0.73
     ſtate
    -0.72
    /*
    -0.71
    saraba
    -0.71
    POSITIVE LOGITS
    <bos>
    0.57
     كومونز
    0.56
     initComponents
    0.51
     panel
    0.50
     thuyết
    0.48
     panels
    0.45
    raborty
    0.45
     His
    0.43
     pan
    0.43
     his
    0.42
    Activations Density 0.042%

    No Known Activations