© 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. 4-CLT-HP
    7. 745
    Prev
    Next
    INDEX
    Explanations

    lot

    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
    достатки
    -0.60
     enfans
    -0.58
     démocr
    -0.55
     sauvages
    -0.50
     zelve
    -0.50
     Majefty
    -0.47
     avoient
    -0.47
     Dok
    -0.46
     verbinding
    -0.46
     voordeel
    -0.46
    POSITIVE LOGITS
     المعيارى
    0.87
    Composable
    0.67
    rylic
    0.63
    úgó
    0.55
     ffilmiau
    0.55
    providedIn
    0.54
    webElementXpaths
    0.53
     Vikipedi
    0.52
     safer
    0.52
    AccessorTable
    0.52
    Activations Density 0.004%

    No Known Activations