© 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. 39003
    Prev
    Next
    INDEX
    Explanations

    conflicting or offending

    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
     conflicting
    -0.82
     competing
    -0.71
     상세
    -0.57
     themſelves
    -0.56
     tutkim
    -0.55
     surviving
    -0.54
    новништво
    -0.53
     disparate
    -0.53
     uſed
    -0.53
    umumkan
    -0.51
    POSITIVE LOGITS
    contentLoaded
    0.63
    afu
    0.61
    YOND
    0.56
    utives
    0.55
    hoeddwyd
    0.55
    })->
    0.55
    WebVitals
    0.53
    APORE
    0.53
    bonnet
    0.53
    ing
    0.52
    Activations Density 0.128%

    No Known Activations