© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5070
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    出版年
    -0.67
    èdia
    -0.61
    AttributeSet
    -0.51
    DoubleQuotes
    -0.48
     transcriptional
    -0.43
    rawtypes
    -0.43
    TabStop
    -0.42
     ارش
    -0.42
    UIFont
    -0.41
     œuvre
    -0.41
    POSITIVE LOGITS
    addPreferredGap
    0.68
    Autoritní
    0.60
    cellaneous
    0.59
     initComponents
    0.59
     more
    0.58
     étudi
    0.53
    gı
    0.52
    Хьажоргаш
    0.52
     étoit
    0.51
    Jeografia
    0.51
    Activations Density 0.001%

    No Known Activations