© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    political figures/politics

    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
    cente
    -0.58
     متعلقه
    -0.55
    WithIOException
    -0.53
     <=",
    -0.48
    ConfigureAwait
    -0.47
    ULO
    -0.46
    برو
    -0.46
    __":
    -0.46
    )?;
    -0.45
    complexContent
    -0.45
    POSITIVE LOGITS
     ji
    0.72
     EdgeInsets
    0.59
     actionPerformed
    0.57
     Ji
    0.55
     uska
    0.54
     cellpadding
    0.52
     Fad
    0.51
     Rij
    0.50
     government
    0.49
     ***!
    0.49
    Activations Density 0.004%

    No Known Activations