© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13150
    Prev
    Next
    INDEX
    Explanations

    helping verbs

    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
    id
    -0.50
    ja
    -0.50
    <eos>
    -0.47
    ↵↵
    -0.47
    ag
    -0.46
    se
    -0.46
    ↵
    -0.45
    agi
    -0.45
     development
    -0.45
    sr
    -0.45
    POSITIVE LOGITS
    رشف
    1.08
     <=",
    1.05
    .")
    0.99
    ✨:
    0.95
    GraphicsUnit
    0.95
     Shakspeare
    0.94
     """
    0.93
     Cæsar
    0.92
     Efq
    0.91
     saites
    0.91
    Activations Density 0.502%

    No Known Activations