© 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. 5-CLT-HP
    7. 6128
    Prev
    Next
    INDEX
    Explanations

    sharing links/forum posts

    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
    localctx
    -0.52
     descal
    -0.47
    webElementXpaths
    -0.47
     mycelium
    -0.47
     Krueger
    -0.47
    ⓘ
    -0.46
     Cracking
    -0.44
    ۜ
    -0.43
     tubeless
    -0.43
     Nile
    -0.43
    POSITIVE LOGITS
     مرئيه
    0.76
     utafitiHapana
    0.66
     متعلقه
    0.64
    出版年
    0.63
    Personensuche
    0.60
    #+#
    0.60
    thâu
    0.57
    stateProvider
    0.55
     виправивши
    0.54
     ModelExpression
    0.53
    Activations Density 0.047%

    No Known Activations