© 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. 4-CLT-HP
    7. 4423
    Prev
    Next
    INDEX
    Explanations

    emon

    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
    Hentet
    -0.68
    httphttps
    -0.60
     للمعارف
    -0.60
    لينكات
    -0.56
    
    -0.56
    ation
    -0.56
    obacterium
    -0.55
     TextAppearance
    -0.54
     censiti
    -0.54
    useState
    -0.53
    POSITIVE LOGITS
    tic
    0.58
    tico
    0.46
    bla
    0.44
    tick
    0.44
    richTextPanel
    0.42
    jgl
    0.40
    ilation
    0.38
    BGP
    0.38
    blaze
    0.38
    NRAS
    0.36
    Activations Density 0.002%

    No Known Activations