© 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. 9005
    Prev
    Next
    INDEX
    Explanations

    ership

    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
    orship
    -3.64
    ership
    -1.88
    ERSHIP
    -1.50
    irmanship
    -0.97
     avoient
    -0.97
    Tembelea
    -0.94
     étoit
    -0.93
    atorship
    -0.93
    yship
    -0.85
    IntoConstraints
    -0.82
    POSITIVE LOGITS
     bat
    0.49
    inien
    0.47
    Dat
    0.46
    GetKeyDown
    0.46
     Dat
    0.46
     Date
    0.44
     Bat
    0.43
    dat
    0.42
     تجمعات
    0.42
     arra
    0.40
    Activations Density 0.036%

    No Known Activations