© 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. 5-CLT-HP
    7. 2716
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
     INSEE
    -0.52
    UnsafeEnabled
    -0.52
     Fillmore
    -0.51
    ➯
    -0.49
    ?}",
    -0.49
    ollectionView
    -0.49
     Picchu
    -0.49
    Glej
    -0.48
    Sectors
    -0.48
     Aguilera
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.59
     cherchés
    0.57
    rungsseite
    0.53
     snippetHide
    0.52
    Coming
    0.51
    ⓧ
    0.50
    contentLoaded
    0.48
     Kupfer
    0.46
    Referències
    0.46
     aims
    0.46
    Activations Density 0.031%

    No Known Activations