© 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. 92076
    Prev
    Next
    INDEX
    Explanations

    hire

    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
     Dio
    -0.91
    hire
    -0.79
     a
    -0.59
     the
    -0.58
    HIRE
    -0.50
     We
    -0.50
     "
    -0.49
     “
    -0.48
    orial
    -0.47
     [[
    -0.46
    POSITIVE LOGITS
     myſelf
    0.98
     ſever
    0.96
     auffi
    0.94
     itſelf
    0.92
     Monfieur
    0.91
     ſind
    0.87
     himſelf
    0.87
     ſtate
    0.85
     reaſon
    0.85
     ſeveral
    0.84
    Activations Density 1.556%

    No Known Activations