© 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. 0-CLT-HP
    7. 92062
    Prev
    Next
    INDEX
    Explanations

    anger/apologies

    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
     street
    -0.99
    street
    -0.91
     angry
    -0.79
    Street
    -0.76
    STREET
    -0.65
    <?,
    -0.62
     STREET
    -0.62
     anger
    -0.60
     streets
    -0.57
     unpleasant
    -0.57
    POSITIVE LOGITS
    存于互联网档案馆
    0.64
    Saluti
    0.61
    álló
    0.61
     חיצוניים
    0.60
     pageContext
    0.51
    libft
    0.50
    วะ
    0.50
    קישורים
    0.49
    Competitive
    0.49
    __':
    0.48
    Activations Density 1.599%

    No Known Activations