© 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. 91136
    Prev
    Next
    INDEX
    Explanations

    system

    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
    endpush
    -0.71
     فريبيس
    -0.69
    Zeneca
    -0.67
     snippetHide
    -0.60
    berdayakan
    -0.60
    brainly
    -0.60
    ########.
    -0.57
     vectorielles
    -0.56
     OFDb
    -0.56
    $_['
    -0.55
    POSITIVE LOGITS
    الإنجليزية
    0.54
    AutoField
    0.51
    XmlAccessorType
    0.50
     failure
    0.47
    EditorBrowsable
    0.46
     ролях
    0.45
    فحة
    0.43
     bonded
    0.43
     connection
    0.42
     cables
    0.42
    Activations Density 1.863%

    No Known Activations