© 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. 5-CLT-HP
    7. 92230
    Prev
    Next
    INDEX
    Explanations

    excessive

    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
     Too
    -0.99
    Too
    -0.94
     too
    -0.89
     TOO
    -0.85
     слишком
    -0.81
    too
    -0.79
    すぎて
    -0.77
     terlalu
    -0.75
    すぎ
    -0.74
     demasi
    -0.73
    POSITIVE LOGITS
    RTLR
    0.67
    XmlRootElement
    0.67
    EndInit
    0.64
     Geraadpleegd
    0.62
    +#+#
    0.59
    UnifiedTopology
    0.57
    Geplaatst
    0.56
    })));
    0.56
    nocache
    0.55
    Aktualisiert
    0.54
    Activations Density 0.010%

    No Known Activations