© 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. 4-CLT-HP
    7. 2870
    Prev
    Next
    INDEX
    Explanations

    1

    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
    mybatisplus
    -0.69
    TEMPO
    -0.63
    AsUp
    -0.61
    ValueStyle
    -0.60
    ьаж
    -0.59
    ArrowToggle
    -0.57
    abestanden
    -0.57
    TabStop
    -0.56
    Демографія
    -0.56
    BASEPATH
    -0.55
    POSITIVE LOGITS
    zyl
    0.58
    endwhile
    0.55
    ingue
    0.52
     alky
    0.50
    $.}
    0.49
    cken
    0.49
    ekyll
    0.48
    な
    0.48
    '));
    0.47
    yethylene
    0.47
    Activations Density 0.001%

    No Known Activations