© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94640
    Prev
    Next
    INDEX
    Explanations

    news reporting

    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
    InputTagHelper
    -0.57
    subpackage
    -0.55
     they
    -0.52
    principalColumn
    -0.51
    withIdentifier
    -0.49
    RectangleBorder
    -0.48
    thien
    -0.47
     showing
    -0.47
     Mexique
    -0.47
    ScopeManager
    -0.46
    POSITIVE LOGITS
    quelize
    0.65
     Walkover
    0.63
    MENAFN
    0.62
     AppCompatTheme
    0.61
     PopupWindow
    0.58
    getActivity
    0.55
     Pattern
    0.55
     Creativity
    0.54
     Réponses
    0.52
    CloseOperation
    0.51
    Activations Density 0.003%

    No Known Activations