© 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. 4639
    Prev
    Next
    INDEX
    Explanations

    bathrooms/bathing

    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
     pady
    -0.40
    tiden
    -0.40
    ềm
    -0.38
     introduction
    -0.37
    гули
    -0.36
     said
    -0.36
    gesetzt
    -0.35
     belief
    -0.35
    hast
    -0.35
    verk
    -0.35
    POSITIVE LOGITS
     незавершена
    1.07
    WebVitals
    1.05
     utafitiHapana
    0.91
    enderror
    0.88
     protoimpl
    0.87
     <=",
    0.86
    Personendaten
    0.84
    Демографія
    0.83
    ⓧ
    0.82
     ligiloj
    0.81
    Activations Density 0.029%

    No Known Activations