© 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. 94378
    Prev
    Next
    INDEX
    Explanations

    estimation

    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
     estimation
    -0.59
     estimations
    -0.52
     imagination
    -0.52
    estimation
    -0.49
     imaginations
    -0.47
     sorrow
    -0.46
    pretation
    -0.46
    ご了承
    -0.46
    y
    -0.46
     son
    -0.45
    POSITIVE LOGITS
     оригіналу
    0.70
    脚注の使い方
    0.67
    Viitteet
    0.66
    ^(@)
    0.66
     Italijani
    0.66
    ists
    0.65
     referenties
    0.65
    Vidite
    0.65
    Santis
    0.65
    MessageOf
    0.65
    Activations Density 1.617%

    No Known Activations