© 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. 0-CLT-HP
    7. 95608
    Prev
    Next
    INDEX
    Explanations

    Staying/remaining

    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
    Negative Logits
    Staying
    -1.00
     Staying
    -0.89
     staying
    -0.79
    PerformLayout
    -0.74
    aarrggbb
    -0.68
     '\\;'
    -0.66
    ########.
    -0.65
    stay
    -0.64
     outs
    -0.63
     Meksiku
    -0.63
    POSITIVE LOGITS
    ed
    0.83
    ian
    0.59
    ement
    0.59
    ists
    0.59
    ie
    0.56
    ette
    0.55
    eer
    0.55
    ίδα
    0.54
    getragen
    0.54
    getSupport
    0.53
    Activations Density 1.671%

    No Known Activations