© 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. 4-CLT-HP
    7. 223
    Prev
    Next
    INDEX
    Explanations

    "on the other hand"

    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
    లాలు
    -0.58
     zwar
    -0.54
     spéc
    -0.54
    Specifically
    -0.53
     stället
    -0.52
    imanapun
    -0.49
     antemano
    -0.48
    Elő
    -0.47
     cará
    -0.46
     recém
    -0.46
    POSITIVE LOGITS
    <bos>
    0.78
     the
    0.72
    MemoryWarning
    0.70
     momenta
    0.63
     optimization
    0.58
     it
    0.56
     الاطلاع
    0.56
     measurements
    0.56
     dispersal
    0.54
     all
    0.54
    Activations Density 0.005%

    No Known Activations