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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38257
    Prev
    Next
    INDEX
    Explanations

    learning and focus

    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
     librement
    -0.56
     épais
    -0.55
     versioni
    -0.54
     semula
    -0.53
     savent
    -0.53
     chauffage
    -0.52
     profondità
    -0.52
     profondeur
    -0.52
     ulteriori
    -0.52
     moindre
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.66
    URLException
    0.63
    ]--;
    0.63
     prompt
    0.62
     graph
    0.61
    "}>
    0.60
     stack
    0.60
     environment
    0.59
     recipe
    0.59
    principalColumn
    0.59
    Activations Density 0.054%

    No Known Activations