© 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. 0-CLT-HP
    7. 95777
    Prev
    Next
    INDEX
    Explanations

    BER

    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
    ber
    -0.74
    BER
    -0.71
     ber
    -0.57
    bers
    -0.50
    Ber
    -0.50
     (
    -0.48
    <b>
    -0.46
     
    -0.46
    .
    -0.44
    <tr>
    -0.44
    POSITIVE LOGITS
     itſelf
    1.24
     CreateTagHelper
    1.09
     Anſ
    1.09
     Efq
    1.08
     myſelf
    1.03
    ^(@)
    1.02
    BibitemShut
    1.01
    ſelf
    1.00
    neſs
    0.97
     Theſe
    0.97
    Activations Density 0.054%

    No Known Activations