© 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. 5-CLT-HP
    7. 5545
    Prev
    Next
    INDEX
    Explanations

    Locations and companies

    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
    Identyfik
    -0.51
     AssemblyVersion
    -0.47
     activités
    -0.46
    ///</
    -0.45
     listos
    -0.42
     []).
    -0.42
    SharedDtor
    -0.41
     rapporti
    -0.41
     παρά
    -0.41
    釈
    -0.41
    POSITIVE LOGITS
     propOrder
    0.74
    AxisAlignment
    0.64
    GraphicsUnit
    0.64
    HttpFoundation
    0.63
     Silo
    0.63
     MainAxisSize
    0.59
     GenerationType
    0.59
    fhir
    0.58
    $_['
    0.57
    quitous
    0.57
    Activations Density 0.001%

    No Known Activations