© 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. 91034
    Prev
    Next
    INDEX
    Explanations

    fact

    np_max-act · gemini-2.0-flash

    fact

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     fact
    -3.42
    fact
    -2.41
     Fact
    -2.02
    Fact
    -2.00
     Tatsache
    -2.00
     fato
    -1.81
     FACT
    -1.72
     fakta
    -1.68
     hecho
    -1.63
     facts
    -1.60
    POSITIVE LOGITS
     that
    0.71
     समीक्षाओं
    0.65
    Personendaten
    0.65
    setVerticalGroup
    0.62
    flashdata
    0.60
    findpost
    0.58
    ,
    0.58
    GEBURTSDATUM
    0.56
    !*\
    0.56
     initComponents
    0.56
    Activations Density 0.026%

    No Known Activations