© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76376
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act-logits · 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
    meisterschaften
    -0.54
     vuotta
    -0.52
    tonode
    -0.48
    šinou
    -0.48
     suivantes
    -0.48
     réduite
    -0.47
     imprimée
    -0.46
    liceerd
    -0.45
    Collegamenti
    -0.45
     françaises
    -0.45
    POSITIVE LOGITS
    ,
    1.51
     there
    0.81
     the
    0.78
    ;
    0.74
     your
    0.68
     an
    0.62
     otomatig
    0.61
     a
    0.60
    RectangleBorder
    0.59
     one
    0.58
    Activations Density 0.001%

    No Known Activations