© 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. 1-CLT-HP
    7. 15332
    Prev
    Next
    INDEX
    Explanations

    Protective, attractive, or domestic

    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
     betweenstory
    -0.86
    aarrggbb
    -0.66
    InjectAttribute
    -0.66
    Domestic
    -0.59
    MessageOf
    -0.58
     Domestic
    -0.56
    OGND
    -0.56
     smtplib
    -0.55
     Италијани
    -0.55
     domestically
    -0.54
    POSITIVE LOGITS
     дописавши
    0.52
     race
    0.52
    XmlAccessorType
    0.50
    __(/*!
    0.50
    בע
    0.50
     finger
    0.49
    Mui
    0.49
    Bele
    0.49
    ceği
    0.49
    CPtr
    0.48
    Activations Density 0.017%

    No Known Activations