© 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. 92395
    Prev
    Next
    INDEX
    Explanations

    first-person perspective

    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
    AccessorTable
    -0.39
     saling
    -0.35
     neler
    -0.35
    devServer
    -0.35
    Chham
    -0.34
     harmonize
    -0.33
     все
    -0.32
     fono
    -0.31
     jointly
    -0.31
     autorytatywna
    -0.31
    POSITIVE LOGITS
     Myself
    0.73
    Enllaces
    0.71
     myself
    0.70
     My
    0.69
     []:
    0.68
     <>",
    0.67
     Became
    0.66
    onomian
    0.65
     Am
    0.64
    AndEndTag
    0.64
    Activations Density 0.014%

    No Known Activations