© 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. 1-CLT-HP
    7. 16007
    Prev
    Next
    INDEX
    Explanations

    cluster

    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
     cliquez
    -0.55
    principalTable
    -0.52
    MessageOf
    -0.50
     שוליים
    -0.50
    icide
    -0.49
    crites
    -0.49
    vedev
    -0.48
     wenig
    -0.48
     jsPsych
    -0.48
    <bos>
    -0.48
    POSITIVE LOGITS
    thenReturn
    0.60
     ujednoznacz
    0.54
     wikipagina
    0.53
    Nhi
    0.53
    escaping
    0.51
     terug
    0.50
    NavController
    0.50
    NameInMap
    0.49
     Doy
    0.49
     postres
    0.48
    Activations Density 0.075%

    No Known Activations