© 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. 16083
    Prev
    Next
    INDEX
    Explanations

    deal

    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
     da
    -0.50
    si
    -0.48
     tar
    -0.47
     sp
    -0.46
     deal
    -0.45
    uis
    -0.43
    u
    -0.42
    uta
    -0.42
    se
    -0.41
    unt
    -0.41
    POSITIVE LOGITS
    舺
    0.69
    Rujuakan
    0.67
     doubtnut
    0.66
    tvguidetime
    0.66
     playmobil
    0.65
     >=",
    0.65
     htons
    0.65
    ernalia
    0.64
     réaliste
    0.63
     Efq
    0.63
    Activations Density 0.031%

    No Known Activations