© 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. 5840
    Prev
    Next
    INDEX
    Explanations

    Programming/Code

    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
     simplest
    -0.54
     instantly
    -0.50
     instant
    -0.47
     Instantly
    -0.46
     hidupnya
    -0.45
    PRNewswire
    -0.44
    yled
    -0.43
     simple
    -0.42
     nonexistent
    -0.42
     first
    -0.42
    POSITIVE LOGITS
     BoxDecoration
    0.83
     يتيمه
    0.81
     lenker
    0.75
     nakalista
    0.74
     Paglinawan
    0.72
    Referanser
    0.71
    ̍t
    0.71
    EndInit
    0.70
     transfieras
    0.70
    +#+
    0.69
    Activations Density 0.003%

    No Known Activations