© 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. 77746
    Prev
    Next
    INDEX
    Explanations

    Sentence snippets

    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
    __);
    -0.54
     performed
    -0.52
     spawned
    -0.51
     sprayed
    -0.51
     implemented
    -0.51
     replaces
    -0.50
     ""],
    -0.49
     ersetzen
    -0.49
     probed
    -0.49
     waived
    -0.48
    POSITIVE LOGITS
    EndProject
    0.58
    Personensuche
    0.50
     δὲ
    0.49
     vérit
    0.48
     Wikimedijinoj
    0.48
    PHeader
    0.48
    oa̍t
    0.48
     avoit
    0.47
     Theſe
    0.46
     scolaires
    0.46
    Activations Density 0.004%

    No Known Activations