© 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. 4-CLT-HP
    7. 2306
    Prev
    Next
    INDEX
    Explanations

    commonly

    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
     part
    -0.57
     change
    -0.52
     component
    -0.47
     portion
    -0.46
     thing
    -0.45
    geord
    -0.45
     excuse
    -0.45
    expandindo
    -0.45
    CloseOperation
    -0.45
     claim
    -0.45
    POSITIVE LOGITS
     BoxFit
    0.75
     proprement
    0.73
     médicaux
    0.68
     fidélité
    0.65
     définiti
    0.65
     démocr
    0.64
     librement
    0.64
     positifs
    0.63
     avoient
    0.62
     bestaande
    0.62
    Activations Density 0.001%

    No Known Activations