© 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. 6219
    Prev
    Next
    INDEX
    Explanations

    Kawasaki

    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
     متعلقه
    -0.78
     InputDecoration
    -0.72
     autorytatywna
    -0.70
    openha
    -0.70
    KommentareTeilen
    -0.69
    таратура
    -0.69
    })));
    -0.68
    httphttps
    -0.66
    ])));
    -0.66
    GenerationType
    -0.64
    POSITIVE LOGITS
     Yvette
    0.52
     ActionResult
    0.46
    getActiveSheet
    0.46
     GridView
    0.45
     Polda
    0.45
     splen
    0.44
    =$?
    0.44
     sauce
    0.43
     reactivity
    0.43
     dAtA
    0.42
    Activations Density 0.002%

    No Known Activations