© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3465
    Prev
    Next
    INDEX
    Explanations

    code, names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    saver
    -0.62
    </tfoot>
    -0.54
     Blazers
    -0.53
    adalajara
    -0.51
    łać
    -0.51
    gameserver
    -0.50
    enschappelijke
    -0.50
    ency
    -0.50
     InputDecoration
    -0.50
    GraphicsUnit
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    0.62
     يتيمه
    0.60
    Kaynakça
    0.55
    __*/
    0.55
     تانيه
    0.53
     rând
    0.52
     émotions
    0.52
     épais
    0.51
     autorytatywna
    0.51
    tagHelperRunner
    0.51
    Activations Density 0.002%

    No Known Activations