© 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. 92166
    Prev
    Next
    INDEX
    Explanations

    American

    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
     American
    -1.09
    American
    -0.99
     american
    -0.98
     AMERICAN
    -0.90
    american
    -0.85
    AMERICAN
    -0.82
     kasarigan
    -0.74
    Americans
    -0.71
     Americans
    -0.70
     américaine
    -0.69
    POSITIVE LOGITS
     يتيمه
    0.65
     HasFactory
    0.64
     Tragedy
    0.62
     Delegation
    0.56
     Else
    0.54
    contentLoaded
    0.54
    Individ
    0.54
    ynchronously
    0.53
     Majefty
    0.53
     voeten
    0.53
    Activations Density 0.025%

    No Known Activations