© 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. 20-CLT-HP
    7. 71340
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    np_max-act-logits · 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
    Autoritní
    -0.61
     ModelExpression
    -0.60
    хьтан
    -0.60
     estimés
    -0.56
     disambiguazione
    -0.56
     Efq
    -0.55
     كورة
    -0.52
     '\\;'
    -0.52
    ⤹
    -0.51
    greja
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.74
    SequentialGroup
    0.62
    帖最后由
    0.59
     TextAppearance
    0.55
    +:+
    0.52
     kasarigan
    0.50
    发表于
    0.49
     Min
    0.49
     system
    0.47
    Buen
    0.47
    Activations Density 0.001%

    No Known Activations