© 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. 1-CLT-HP
    7. 10403
    Prev
    Next
    INDEX
    Explanations

    scientific/technical context

    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
    ellants
    -0.63
    脚注の使い方
    -0.60
     Divider
    -0.54
    findpost
    -0.52
     للاسماء
    -0.50
    
    -0.49
    RILL
    -0.49
     disponibilités
    -0.48
    \{\\
    -0.48
    ukų
    -0.48
    POSITIVE LOGITS
     désolés
    0.58
    دانشنامهٔ
    0.57
    runApp
    0.55
     '\\;'
    0.53
    Tikang
    0.52
    makeConstraints
    0.51
     ApiException
    0.50
     ContentValues
    0.50
    XmlAccessorType
    0.50
     /\.
    0.50
    Activations Density 0.108%

    No Known Activations