© 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. 97081
    Prev
    Next
    INDEX
    Explanations

    War, cigars

    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
    AddTagHelper
    -0.86
     %@",
    -0.56
     cherchés
    -0.56
    ?";
    -0.55
    \{\\
    -0.54
    ()");
    -0.54
     стаття
    -0.53
    iações
    -0.52
    %");
    -0.51
    %";
    -0.50
    POSITIVE LOGITS
    IndentedString
    0.54
     IndexPath
    0.51
    Bibliograf
    0.50
    poptosis
    0.47
    GEBURTSDATUM
    0.47
    inį
    0.47
    UnsafeEnabled
    0.46
    ształ
    0.46
     fometimes
    0.46
     Gaby
    0.45
    Activations Density 0.000%

    No Known Activations