© 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. 0-CLT-HP
    7. 90527
    Prev
    Next
    INDEX
    Explanations

    boost

    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
     V
    -0.46
    DockStyle
    -0.46
    EReference
    -0.46
    monition
    -0.45
     Per
    -0.45
    Vidite
    -0.43
    interopRequire
    -0.43
    PhysRevLett
    -0.42
     F
    -0.42
     
    -0.42
    POSITIVE LOGITS
     Theſe
    0.93
     Monfieur
    0.93
     itſelf
    0.90
    Демографія
    0.83
     themſelves
    0.82
    GEBURTSDATUM
    0.82
     myſelf
    0.81
     houſe
    0.80
     Jefus
    0.77
     himſelf
    0.75
    Activations Density 0.144%

    No Known Activations