© 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. 6307
    Prev
    Next
    INDEX
    Explanations

    code and syntax fragments

    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
    Geplaatst
    -0.49
     Decade
    -0.47
    CodeDom
    -0.47
    BeginContext
    -0.46
     '\\;'
    -0.46
    SceneManagement
    -0.45
    !*\
    -0.43
    withIdentifier
    -0.43
     helyez
    -0.43
     BoxFit
    -0.42
    POSITIVE LOGITS
    AnchorStyles
    0.57
     mergeFrom
    0.56
    ends
    0.56
     jScrollPane
    0.53
    endphp
    0.52
    upar
    0.50
    ])).
    0.48
    abay
    0.48
    zyż
    0.48
    up
    0.47
    Activations Density 0.000%

    No Known Activations