© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4133
    Prev
    Next
    INDEX
    Explanations

    the

    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
    afficheront
    -0.63
    rawDesc
    -0.60
     AssemblyCompany
    -0.59
     inégal
    -0.59
    stateProvider
    -0.58
    Personensuche
    -0.57
    IVEREF
    -0.57
     protoimpl
    -0.56
    Tikang
    -0.54
    ValueStyle
    -0.54
    POSITIVE LOGITS
     సౌకర్య
    0.55
    ViewGroup
    0.48
    iorgio
    0.47
    ONAUT
    0.47
     contributing
    0.47
     concerned
    0.45
     volume
    0.45
    RenderAtEndOf
    0.45
    شهاد
    0.45
     staying
    0.44
    Activations Density 0.001%

    No Known Activations