© 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. 20-CLT-HP
    7. 76634
    Prev
    Next
    INDEX
    Explanations

    code

    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
     لينك
    -0.64
     '/';
    -0.57
     Fidel
    -0.51
     paroisse
    -0.50
     Nikita
    -0.49
     "/";
    -0.48
    GEBURTSDATUM
    -0.48
     parietal
    -0.47
    esai
    -0.47
     '-';
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.55
     AssemblyCompany
    0.51
    RegressionTest
    0.48
    ResumeLayout
    0.48
    enumii
    0.47
    makeText
    0.45
    EditorBrowsable
    0.45
     CVC
    0.45
     RVA
    0.45
    RuleContext
    0.45
    Activations Density 0.000%

    No Known Activations