© 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. 45038
    Prev
    Next
    INDEX
    Explanations

    talking about people

    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
     guys
    -1.09
     guy
    -1.05
    guys
    -0.99
     folks
    -0.97
     GUYS
    -0.94
     Guys
    -0.92
    Guys
    -0.92
    Folks
    -0.84
     Comprehensive
    -0.80
     Folks
    -0.79
    POSITIVE LOGITS
    
    0.73
    e
    0.73
    TestingModule
    0.69
     nakalista
    0.69
    a
    0.63
    AnchorStyles
    0.57
    SizeF
    0.56
    UnknownFieldSet
    0.54
    >>,
    0.54
    </thead>
    0.53
    Activations Density 0.054%

    No Known Activations