© 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. 4-CLT-HP
    7. 1250
    Prev
    Next
    INDEX
    Explanations

    resignation/withdrawal

    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
    -0.99
    :✨
    -0.90
     kasarigan
    -0.83
     ModelExpression
    -0.74
    ContentAsync
    -0.74
    Rüyada
    -0.73
     nahilalakip
    -0.73
     ISNI
    -0.70
    ManagedBean
    -0.66
    setVerticalGroup
    -0.64
    POSITIVE LOGITS
     from
    0.77
     form
    0.50
     facing
    0.48
    ح
    0.48
    zeera
    0.47
     từ
    0.46
    from
    0.46
    حي
    0.44
     positions
    0.43
     från
    0.42
    Activations Density 0.005%

    No Known Activations