© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 329
    Prev
    Next
    INDEX
    Explanations

    and

    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
    دانشنامهٔ
    -0.81
    
    -0.63
    StoryboardSegue
    -0.60
    MessageOf
    -0.60
    #+#
    -0.59
    SaveChangesAsync
    -0.59
    Personensuche
    -0.59
    ViewImports
    -0.58
     Wachs
    -0.57
    клопе
    -0.57
    POSITIVE LOGITS
     thirteen
    0.66
     fourteen
    0.65
     eleven
    0.64
     seven
    0.63
     sixteen
    0.60
     eight
    0.58
     nine
    0.58
     five
    0.58
     ten
    0.57
     seventeen
    0.56
    Activations Density 0.010%

    No Known Activations