© 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. 71641
    Prev
    Next
    INDEX
    Explanations

    Foreign words/symbols

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.98
    rrggbb
    -0.71
    InstanceState
    -0.66
    queryInterface
    -0.66
     initComponents
    -0.66
    SOUNDBITE
    -0.65
    RegressionTest
    -0.65
     ActionResult
    -0.63
    reportWebVitals
    -0.63
     Reverb
    -0.60
    POSITIVE LOGITS
    वान
    0.44
    GPP
    0.40
    uffff
    0.40
    principalTable
    0.40
    دود
    0.39
    glich
    0.38
    stris
    0.38
    AnchorTagHelper
    0.38
    ništ
    0.37
    yyyyy
    0.36
    Activations Density 0.000%

    No Known Activations