© 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. 14407
    Prev
    Next
    INDEX
    Explanations

    IA

    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
    protoc
    -0.60
     pageable
    -0.55
    OGND
    -0.54
     ligiloj
    -0.50
    InsertCommand
    -0.48
    diğim
    -0.47
    ÜR
    -0.46
    Juni
    -0.45
     edges
    -0.44
    Frontier
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.72
    Parcelize
    0.60
     Seeder
    0.60
     مشين
    0.58
    emmel
    0.56
    homonymie
    0.55
    HasAnnotation
    0.55
     محفوظة
    0.54
    aculture
    0.54
    tionally
    0.54
    Activations Density 0.026%

    No Known Activations