© 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. 4-CLT-HP
    7. 3454
    Prev
    Next
    INDEX
    Explanations

    article a/an

    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
    TypeMap
    -0.44
     
    -0.43
     “
    -0.40
     "
    -0.39
    deal
    -0.39
    </b>
    -0.37
    سع
    -0.37
     comfy
    -0.36
     deal
    -0.36
     program
    -0.35
    POSITIVE LOGITS
     '\\;'
    0.78
     الحره
    0.77
    __':
    0.75
    ViewImports
    0.75
     AttributeSet
    0.74
     vraag
    0.73
    <bos>
    0.71
     initComponents
    0.70
    LEncoder
    0.70
     InputDecoration
    0.69
    Activations Density 0.017%

    No Known Activations