© 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. 39851
    Prev
    Next
    INDEX
    Explanations

    political/organizational

    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
     Majefty
    -1.15
    AddTagHelper
    -1.11
     myſelf
    -1.09
    ſelf
    -1.05
     ―――――
    -1.04
     Jefus
    -1.03
     Monfieur
    -1.03
     itſelf
    -1.02
    WebVitals
    -0.97
     Cæsar
    -0.96
    POSITIVE LOGITS
    er
    0.85
    is
    0.82
    e
    0.77
    on
    0.76
    se
    0.75
    es
    0.74
    om
    0.73
    us
    0.72
    ale
    0.69
    al
    0.68
    Activations Density 0.079%

    No Known Activations