© 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. 1161
    Prev
    Next
    INDEX
    Explanations

    There

    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
    _'.$
    -0.62
    :✨
    -0.59
     There
    -0.52
    /**/*.
    -0.50
    ">:
    -0.50
    _'+
    -0.49
     '/':
    -0.49
     ';
    
    -0.49
     oneself
    -0.49
     yarn
    -0.48
    POSITIVE LOGITS
     wireType
    0.68
     was
    0.67
    for
    0.63
    ViewFeatures
    0.63
     mourut
    0.61
    not
    0.61
     is
    0.60
     فريبيس
    0.59
    fois
    0.59
    จึง
    0.59
    Activations Density 0.047%

    No Known Activations