© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97369
    Prev
    Next
    INDEX
    Explanations

    references to

    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
     preuves
    -0.56
     slutet
    -0.47
     for
    -0.46
     reú
    -0.45
     untersuchen
    -0.44
     Tất
    -0.44
     merve
    -0.44
     ngăn
    -0.43
     vœux
    -0.42
     olun
    -0.42
    POSITIVE LOGITS
    aarrggbb
    0.79
    ]")]
    0.69
     ModelExpression
    0.68
     jScrollPane
    0.67
    CloseOperation
    0.67
    
    0.66
    migrationBuilder
    0.66
     ModelRenderer
    0.66
    featureID
    0.65
    findpost
    0.65
    Activations Density 0.001%

    No Known Activations