© 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. 76958
    Prev
    Next
    INDEX
    Explanations

    well or round

    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
    principalTable
    -0.81
     indépendante
    -0.66
     mauvaises
    -0.63
    URLException
    -0.61
    TagMode
    -0.59
     IBOutlet
    -0.59
    </thead>
    -0.58
     SafeMath
    -0.58
     indépend
    -0.57
     neutre
    -0.57
    POSITIVE LOGITS
     well
    1.37
     rounded
    1.20
     round
    1.13
     Well
    1.06
    Well
    1.02
    rounded
    0.98
     rounds
    0.98
    well
    0.93
     balanced
    0.88
    round
    0.87
    Activations Density 0.001%

    No Known Activations