© 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. 71522
    Prev
    Next
    INDEX
    Explanations

    code 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
    Negative Logits
     present
    -0.61
     présente
    -0.54
    ioutil
    -0.53
    twimg
    -0.52
     talk
    -0.49
     use
    -0.49
     pray
    -0.49
    khana
    -0.48
    SequentialGroup
    -0.48
    xions
    -0.48
    POSITIVE LOGITS
     linkovi
    0.71
    ########.
    0.66
     ostavi
    0.61
     estimés
    0.59
    WebControls
    0.57
     kaarangay
    0.55
     numerus
    0.55
     give
    0.53
     resourceCulture
    0.53
    Collegamenti
    0.52
    Activations Density 0.000%

    No Known Activations