© 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. 90915
    Prev
    Next
    INDEX
    Explanations

    both each

    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
    <bos>
    -0.56
    Cliquez
    -0.52
    ')):
    -0.50
    __*/
    -0.50
    Kjelder
    -0.49
    pēc
    -0.48
    pakatan
    -0.48
     pihaknya
    -0.48
     solves
    -0.47
    IntoConstraints
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.79
    sohn
    0.55
    GeneratedCode
    0.54
    APORE
    0.52
    Abitanti
    0.52
     BrowserModule
    0.52
    Foi
    0.51
     desto
    0.51
     flowed
    0.51
    UnusedPrivate
    0.51
    Activations Density 0.007%

    No Known Activations