© 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. 93443
    Prev
    Next
    INDEX
    Explanations

    formal writing

    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
    +#+#
    -0.89
     فريبيس
    -0.86
    Portail
    -0.86
    EndInit
    -0.86
     سكانية
    -0.83
     AssemblyCompany
    -0.82
    GEBURTSDATUM
    -0.81
    ResumeLayout
    -0.81
    RegressionTest
    -0.79
    ItemBackground
    -0.78
    POSITIVE LOGITS
     so
    0.56
     lately
    0.50
     antaranya
    0.48
     afin
    0.44
     premier
    0.44
     proprio
    0.42
     conceive
    0.42
    */;
    0.42
     know
    0.41
    خم
    0.41
    Activations Density 0.022%

    No Known Activations