© 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. 6297
    Prev
    Next
    INDEX
    Explanations

    old

    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
     nemlig
    -0.61
     Reisedaten
    -0.57
    THISDAY
    -0.50
    prnewswire
    -0.49
    styleType
    -0.48
    pherals
    -0.47
     löyty
    -0.47
     post
    -0.47
     наоборот
    -0.47
    paramref
    -0.47
    POSITIVE LOGITS
     nakalista
    0.62
     بيها
    0.60
    </tbody>
    0.57
    Obrázky
    0.54
    awtextra
    0.53
    weiser
    0.50
    koľvek
    0.49
    orological
    0.49
     zoveel
    0.48
    DialogContent
    0.48
    Activations Density 0.000%

    No Known Activations