© 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. 95677
    Prev
    Next
    INDEX
    Explanations

    quite

    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
     quite
    -2.72
    quite
    -2.61
    Quite
    -2.56
     Quite
    -2.55
     ganska
    -1.30
     ganske
    -1.27
     destul
    -1.27
     uite
    -1.20
     bastante
    -1.11
     cukup
    -1.04
    POSITIVE LOGITS
     an
    0.56
    ApiModelProperty
    0.54
     a
    0.52
     possibly
    0.52
     the
    0.51
    CrossRef
    0.51
     high
    0.51
     effective
    0.50
     large
    0.50
     rare
    0.50
    Activations Density 0.134%

    No Known Activations