© 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. 5-CLT-HP
    7. 94550
    Prev
    Next
    INDEX
    Explanations

    code

    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
     дописавши
    -0.76
    IUrlHelper
    -0.71
    GraphicsUnit
    -0.65
     resourceCulture
    -0.65
    FTFY
    -0.60
    WebControls
    -0.60
    ỡng
    -0.59
    MemoryWarning
    -0.59
    tvguidetime
    -0.59
    SQLiteDatabase
    -0.59
    POSITIVE LOGITS
    //~
    0.48
    Tikang
    0.47
     Mérimée
    0.46
     Manajemen
    0.45
     possible
    0.45
     gerekiyor
    0.45
     understanding
    0.44
    labus
    0.42
     shed
    0.42
    akyti
    0.41
    Activations Density 0.010%

    No Known Activations