© 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. 5976
    Prev
    Next
    INDEX
    Explanations

    d

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.83
     ujednoznacz
    -0.78
    tvguidetime
    -0.75
    webElementXpaths
    -0.74
    évaluateur
    -0.73
    AccessorTable
    -0.71
    DockStyle
    -0.69
     jScrollPane
    -0.68
    ]--;
    -0.68
     <>",
    -0.68
    POSITIVE LOGITS
     and
    0.59
     good
    0.57
     bonnes
    0.56
    good
    0.56
     or
    0.51
     bonne
    0.51
    DataURL
    0.48
    forRoot
    0.47
    uling
    0.46
     goede
    0.46
    Activations Density 0.028%

    No Known Activations