© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4692
    Prev
    Next
    INDEX
    Explanations

    for

    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
     setting
    -0.56
    axx
    -0.54
    viewDidLoad
    -0.49
     seeing
    -0.48
     selecting
    -0.47
     mere
    -0.47
    setOutput
    -0.46
     example
    -0.46
    étant
    -0.46
     finding
    -0.46
    POSITIVE LOGITS
     MainAxisSize
    0.83
    principalColumn
    0.66
    脚注の使い方
    0.62
    ConstraintMaker
    0.59
     الدولى
    0.58
    InputBorder
    0.57
     referenties
    0.56
     AttributeSet
    0.56
    rature
    0.55
     समीक्षक
    0.53
    Activations Density 0.004%

    No Known Activations