Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73915
    Prev
    Next
    INDEX
    Explanations

    U

    np_max-act-logits · 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
     createState
    -0.54
     doInBackground
    -0.52
    foe
    -0.51
    
    -0.51
    AxisAlignment
    -0.47
     *)__
    -0.47
    tvguidetime
    -0.47
    jsxFileName
    -0.46
    )_/¯
    -0.46
     {?>
    -0.46
    POSITIVE LOGITS
     Gorb
    0.54
    ftagPool
    0.52
     BoxFit
    0.50
    ModelBuilder
    0.49
     Claude
    0.49
    EventLoop
    0.49
    writeHead
    0.48
     círculo
    0.47
     Brescia
    0.47
     Lode
    0.47
    Activations Density 0.003%

    No Known Activations