© 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. 93134
    Prev
    Next
    INDEX
    Explanations

    oglo

    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
     وتسجيلات
    -0.49
    şiv
    -0.48
    Identyfik
    -0.46
    ις
    -0.44
     suggestive
    -0.43
    ymce
    -0.42
    zate
    -0.40
     integrate
    -0.40
    tis
    -0.40
    archi
    -0.40
    POSITIVE LOGITS
    bul
    0.70
     GenerationType
    0.65
    Bul
    0.62
    ChildScrollView
    0.60
     Bul
    0.60
    coroutines
    0.59
     EconPapers
    0.58
    Pue
    0.57
    GraphicsUnit
    0.57
     bul
    0.56
    Activations Density 0.002%

    No Known Activations