© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43315
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    :✨
    -0.70
    antaranya
    -0.69
     betweenstory
    -0.67
     bäst
    -0.62
    AsUp
    -0.61
    berdayakan
    -0.60
    égard
    -0.60
    fromnode
    -0.59
    poň
    -0.58
     Walkover
    -0.57
    POSITIVE LOGITS
    ↵↵
    0.73
    2
    0.69
    0
    0.63
    <strong>
    0.62
    .
    0.62
    C
    0.62
    A
    0.61
    S
    0.61
    ↵
    0.59
    WindowConstants
    0.59
    Activations Density 0.173%

    No Known Activations