© 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. 0-CLT-HP
    7. 41248
    Prev
    Next
    INDEX
    Explanations

    pneum

    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
    ing
    -0.56
    alo
    -0.53
    T
    -0.52
    nor
    -0.52
    hu
    -0.50
    ்த
    -0.49
    pla
    -0.48
     Lou
    -0.48
    rec
    -0.48
    .
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.94
    SequentialGroup
    0.90
    WriteTagHelper
    0.85
     CreateTagHelper
    0.84
    PreferredItem
    0.77
    SBATCH
    0.76
     ControllerBase
    0.76
    saraba
    0.75
    DockStyle
    0.74
    ^(@)
    0.73
    Activations Density 0.179%

    No Known Activations