© 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. 77911
    Prev
    Next
    INDEX
    Explanations

    Technical/academic snippets

    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
     kasarigan
    -0.82
    SourceChecksum
    -0.81
    IntoConstraints
    -0.75
     doInBackground
    -0.63
     opérateur
    -0.61
     ComVisible
    -0.60
     ExecuteAsync
    -0.60
    tagHelperRunner
    -0.60
     <>",
    -0.58
     autorytatywna
    -0.55
    POSITIVE LOGITS
    turn
    0.58
    interopRequire
    0.56
     Turn
    0.53
    Turn
    0.53
    Erreferentziak
    0.52
     Mühle
    0.52
     turner
    0.51
     Turner
    0.51
     flint
    0.49
    acuzzi
    0.49
    Activations Density 0.001%

    No Known Activations