© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14908
    Prev
    Next
    INDEX
    Explanations

    old

    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
     الرياضيه
    -0.85
     viewDidLoad
    -0.82
    InjectAttribute
    -0.77
     pinulongan
    -0.72
    contentLoaded
    -0.72
     InputDecoration
    -0.71
     intptr
    -0.70
    UIControlState
    -0.69
     LoginComponent
    -0.69
     surla
    -0.68
    POSITIVE LOGITS
     flesta
    0.53
    ";
    0.45
    حق
    0.43
     fleste
    0.43
    ishna
    0.43
    ய்ய
    0.43
    salms
    0.43
    nischen
    0.43
    IZAR
    0.42
    Kh
    0.42
    Activations Density 0.003%

    No Known Activations