© 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. 20-CLT-HP
    7. 73132
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · 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
     nahilalakip
    -0.71
    lujah
    -0.52
     noDo
    -0.52
     referenties
    -0.51
    endregion
    -0.49
    ΤΟ
    -0.48
     Савезне
    -0.47
     Castilla
    -0.46
    endpush
    -0.45
    principalColumn
    -0.44
    POSITIVE LOGITS
    LabelTagHelper
    0.59
     Runs
    0.56
    NK
    0.54
     Mald
    0.53
     NKC
    0.53
     vito
    0.52
    MenuGroup
    0.51
     tenuto
    0.50
    ulemon
    0.50
     XRP
    0.49
    Activations Density 0.005%

    No Known Activations