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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95269
    Prev
    Next
    INDEX
    Explanations

    the

    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
     codon
    -0.59
    saraba
    -0.56
     volts
    -0.50
     kettle
    -0.49
    су
    -0.46
    Khach
    -0.45
    ধ্য
    -0.45
    :])
    -0.45
    EDEFAULT
    -0.45
    +'</
    -0.44
    POSITIVE LOGITS
    StructEnd
    0.62
    principalTable
    0.54
    TableAdapter
    0.54
     >=",
    0.52
    djangoproject
    0.52
    Autoritní
    0.52
    ]--;
    0.50
    Portail
    0.49
     externi
    0.49
     विश्वसनीयता
    0.48
    Activations Density 0.004%

    No Known Activations