© 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. 0-CLT-HP
    7. 94786
    Prev
    Next
    INDEX
    Explanations

    adulthood

    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
     adulthood
    -1.23
     childhood
    -0.86
    BeginInit
    -0.83
    IsContent
    -0.82
     adolescence
    -0.81
     pleaſure
    -0.81
     infancy
    -0.78
    HideFlags
    -0.75
     ſtate
    -0.73
     ?>/
    -0.73
    POSITIVE LOGITS
    leaf
    0.46
    ga
    0.46
    file
    0.46
    name
    0.45
    up
    0.45
    ↵
    0.44
    গ
    0.44
    </tr>
    0.43
    if
    0.43
    кал
    0.43
    Activations Density 0.556%

    No Known Activations