© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93488
    Prev
    Next
    INDEX
    Explanations

    mechan

    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
     ter
    -0.71
     ment
    -0.64
     qu
    -0.60
     of
    -0.57
     ant
    -0.55
    tar
    -0.55
    tier
    -0.54
    توان
    -0.54
    a
    -0.52
     tar
    -0.52
    POSITIVE LOGITS
    MemoryWarning
    0.92
    setVerticalGroup
    0.84
     ExecuteAsync
    0.80
    IndentedString
    0.78
    AddTagHelper
    0.73
     autorytatywna
    0.71
    <?
    0.70
     EconPapers
    0.69
    FailureListener
    0.69
    ImageContext
    0.68
    Activations Density 0.719%

    No Known Activations