© 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. 20-CLT-HP
    4. 74600
    Prev
    Next
    INDEX
    Explanations

    biochemistry

    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
     <=",
    -0.67
    tagHelperRunner
    -0.60
     protoimpl
    -0.59
    gabe
    -0.56
    iba
    -0.54
     متعلقه
    -0.53
    bery
    -0.52
    že
    -0.52
    afp
    -0.52
     Care
    -0.51
    POSITIVE LOGITS
    Personendaten
    0.54
    SBATCH
    0.54
     SafeMath
    0.50
     referenties
    0.46
     numberOfRows
    0.44
    loit
    0.43
     Tiss
    0.43
     Мексичка
    0.42
     StatelessWidget
    0.42
     NRC
    0.42
    Activations Density 0.007%

    No Known Activations