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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97679
    Prev
    Next
    INDEX
    Explanations

    only

    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
     only
    -3.55
    only
    -3.06
    Only
    -2.69
     Only
    -2.50
    ONLY
    -2.23
     ONLY
    -2.17
     seulement
    -2.02
     только
    -1.96
     tylko
    -1.91
     hanya
    -1.86
    POSITIVE LOGITS
    awtextra
    0.97
    extAlignment
    0.94
     nakalista
    0.91
     للاسماء
    0.88
    ReusableCell
    0.86
    RenderAtEndOf
    0.85
     resourceCulture
    0.85
     Infórmanos
    0.84
    NOPQRST
    0.81
     विश्वसनीयता
    0.81
    Activations Density 0.066%

    No Known Activations