© 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. 1-CLT-HP
    7. 14117
    Prev
    Next
    INDEX
    Explanations

    news events

    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
    <bos>
    -1.23
     colorés
    -0.54
     erfaring
    -0.53
    Whilst
    -0.52
     løpet
    -0.50
    EntityFramework
    -0.50
     jendela
    -0.50
     Suecia
    -0.49
    Evidence
    -0.48
    uxxxx
    -0.47
    POSITIVE LOGITS
    DeleteBehavior
    0.77
     jScrollPane
    0.75
    numerusform
    0.65
    RegistryLite
    0.63
    PerformLayout
    0.63
    principalTable
    0.61
    setVerticalGroup
    0.61
    SizeMode
    0.59
    isContained
    0.58
    :✨
    0.57
    Activations Density 0.032%

    No Known Activations