© 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. 97970
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Efq
    -0.77
     BoxFit
    -0.77
    IBLIO
    -0.71
     متعلقه
    -0.70
     $_"
    -0.70
    principalTable
    -0.69
     greateſt
    -0.69
    IUrlHelper
    -0.68
     himſelf
    -0.68
     iſt
    -0.68
    POSITIVE LOGITS
     دیکھیے
    0.56
    Now
    0.47
    ,
    0.46
     team
    0.44
    i
    0.43
    a
    0.43
     oprot
    0.41
    There
    0.41
     Now
    0.40
    kol
    0.40
    Activations Density 0.013%

    No Known Activations