© 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. 93788
    Prev
    Next
    INDEX
    Explanations

    purpose

    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
    DockStyle
    -0.86
    +#+#
    -0.79
    Демографія
    -0.73
    /**
    -0.70
    DeleteBehavior
    -0.70
    GroupLayout
    -0.70
     Roskov
    -0.69
     kasarigan
    -0.68
    Personensuche
    -0.68
    IndentedString
    -0.68
    POSITIVE LOGITS
     about
    0.52
     from
    0.50
     handling
    0.49
     running
    0.47
     correndo
    0.47
     contando
    0.47
     on
    0.46
     handled
    0.45
     bowiem
    0.45
     corriendo
    0.45
    Activations Density 0.001%

    No Known Activations