© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4660
    Prev
    Next
    INDEX
    Explanations

    a

    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
     خارجية
    -0.49
    MENAFN
    -0.48
    antía
    -0.47
    ########.
    -0.46
    PositiveButton
    -0.45
    سری
    -0.42
    ticle
    -0.42
     gens
    -0.41
     chinoise
    -0.41
    komendasi
    -0.41
    POSITIVE LOGITS
    MethodManager
    0.65
     experienced
    0.64
     graduate
    0.63
     native
    0.63
     незавершена
    0.62
     ExecuteAsync
    0.62
     AutoMapper
    0.59
     Irish
    0.56
     المعيارى
    0.56
     young
    0.55
    Activations Density 0.003%

    No Known Activations