© 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. 1-CLT-HP
    7. 15035
    Prev
    Next
    INDEX
    Explanations

    list

    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
     list
    -0.83
     lista
    -0.71
     Liste
    -0.71
     LIST
    -0.70
     List
    -0.68
    List
    -0.65
     listing
    -0.65
     liste
    -0.63
    LIST
    -0.59
     listy
    -0.59
    POSITIVE LOGITS
     resourceCulture
    0.64
    styleType
    0.60
    djangoproject
    0.58
     мәкалә
    0.53
     Мексичка
    0.53
     StatelessWidget
    0.52
    ็จ
    0.52
    ens
    0.51
    BuildContext
    0.49
    ыгана
    0.49
    Activations Density 0.013%

    No Known Activations