© 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. 1-CLT-HP
    7. 11789
    Prev
    Next
    INDEX
    Explanations

    plastic and instructions

    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
    sizeCache
    -0.69
     kasarigan
    -0.59
     stockings
    -0.53
     labourers
    -0.53
     treason
    -0.50
    UVWXYZ
    -0.50
    FMC
    -0.49
     sweatpants
    -0.48
     geniuses
    -0.48
     Sarkozy
    -0.47
    POSITIVE LOGITS
    èdia
    0.66
    HtmlAttribute
    0.61
    Personendaten
    0.56
     endregion
    0.54
    Архівовано
    0.54
     ElementRef
    0.52
     BoxFit
    0.52
    ṃ
    0.51
     nakalista
    0.51
     hop
    0.50
    Activations Density 0.039%

    No Known Activations