© 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. 78010
    Prev
    Next
    INDEX
    Explanations

    one

    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
    WithIOException
    -0.77
     ProtoMessage
    -0.75
    EDEFAULT
    -0.70
     Paglinawan
    -0.69
    ThroughAttribute
    -0.65
     Roskov
    -0.64
     utafitiHapana
    -0.61
    complexContent
    -0.60
    utilisons
    -0.59
    SourceChecksum
    -0.59
    POSITIVE LOGITS
    1
    0.65
    +:+
    0.65
    +#+#
    0.52
    はじめに
    0.49
     PhpStorm
    0.49
    lyn
    0.47
    １
    0.45
    .¹
    0.44
    zug
    0.44
    𝟭
    0.43
    Activations Density 0.004%

    No Known Activations