© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71613
    Prev
    Next
    INDEX
    Explanations

    place related words

    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
     stopping
    -0.65
     reaching
    -0.63
     completing
    -0.60
     altering
    -0.60
     cancelling
    -0.59
     canceling
    -0.59
     expressing
    -0.59
     adding
    -0.59
     Мексичка
    -0.59
     falling
    -0.58
    POSITIVE LOGITS
     Hole
    0.55
     Mall
    0.55
     State
    0.51
     Herd
    0.51
     Yard
    0.50
     Common
    0.48
     Cream
    0.47
     Cavity
    0.47
     Side
    0.47
     Hollow
    0.47
    Activations Density 0.000%

    No Known Activations