© 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. 20-CLT-HP
    7. 75230
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act-logits · 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
    rungsseite
    -0.88
    UnusedPrivate
    -0.68
    RegressionTest
    -0.67
     Италијани
    -0.64
     MonoBehaviour
    -0.63
    Personendaten
    -0.60
    ViewImports
    -0.60
    خصة
    -0.60
    HtmlAttribute
    -0.58
    RunAsync
    -0.58
    POSITIVE LOGITS
    eclampsia
    0.42
    webf
    0.40
    الحياه
    0.39
    hdys
    0.38
    mask
    0.38
    uf
    0.38
    achers
    0.38
    ures
    0.38
    pulumi
    0.38
    tach
    0.37
    Activations Density 0.000%

    No Known Activations