© 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. 20-CLT-HP
    7. 75617
    Prev
    Next
    INDEX
    Explanations

    living

    np_max-act-logits · 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
    IntoConstraints
    -0.72
    دانشنامهٔ
    -0.68
     ویکی‌پدیا
    -0.60
    featureID
    -0.59
    oredCriteria
    -0.58
     beginnetje
    -0.57
     StringTokenizer
    -0.55
    ThroughAttribute
    -0.53
    ValueStyle
    -0.51
    CloseOperation
    -0.49
    POSITIVE LOGITS
     living
    0.83
     lives
    0.74
    Living
    0.72
     Living
    0.69
    living
    0.66
    LIVING
    0.65
     Lives
    0.61
     LIVING
    0.61
    lives
    0.59
     alive
    0.58
    Activations Density 0.001%

    No Known Activations