© 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. 5-CLT-HP
    7. 5466
    Prev
    Next
    INDEX
    Explanations

    formal text

    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
    DockStyle
    -1.05
    protoimpl
    -0.96
     تضيفلها
    -0.91
     '\\;'
    -0.87
    Datuak
    -0.81
    XmlAccessType
    -0.79
    OGND
    -0.79
    +:+
    -0.79
    AddTagHelper
    -0.79
    enumii
    -0.77
    POSITIVE LOGITS
    Bioaccumulative
    0.41
     demas
    0.31
    ωση
    0.30
    execSQL
    0.30
    tanleria
    0.29
    GeneratedCode
    0.29
    lunda
    0.29
     princí
    0.29
    Попис
    0.29
    Solución
    0.28
    Activations Density 0.000%

    No Known Activations