© 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. 95463
    Prev
    Next
    INDEX
    Explanations

    together

    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
     against
    -1.86
     together
    -1.81
    against
    -1.74
    Against
    -1.63
    together
    -1.56
     Against
    -1.54
     AGAINST
    -1.54
    Together
    -1.44
     împreună
    -1.44
     tillsammans
    -1.40
    POSITIVE LOGITS
     the
    0.80
     "
    0.74
     a
    0.70
     non
    0.69
     an
    0.68
     '
    0.66
     “
    0.65
     
    0.65
     Bo
    0.64
     ‘
    0.62
    Activations Density 0.074%

    No Known Activations