© 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. 93163
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     CreateTagHelper
    -0.76
    aarrggbb
    -0.74
     newOwner
    -0.72
     AssemblyCulture
    -0.72
     متعلقه
    -0.71
    évaluateur
    -0.69
    ⓧ
    -0.68
     estekak
    -0.67
     Exacts
    -0.65
    peutic
    -0.65
    POSITIVE LOGITS
     welded
    0.65
     ground
    0.61
     clamped
    0.60
     sanded
    0.60
     punctured
    0.58
     washed
    0.58
     clipped
    0.57
     tagged
    0.57
     trimmed
    0.56
     bolted
    0.56
    Activations Density 0.003%

    No Known Activations