© 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. 92046
    Prev
    Next
    INDEX
    Explanations

    jak

    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
     Justice
    -0.96
     justice
    -0.88
    justice
    -0.86
    Justice
    -0.84
     JUSTICE
    -0.83
    ara
    -0.77
    aram
    -0.74
     Justicia
    -0.70
    ARA
    -0.68
    arama
    -0.68
    POSITIVE LOGITS
    tagHelperRunner
    0.62
    Obrázky
    0.57
     maroca
    0.56
    uxxxx
    0.56
     deutschland
    0.55
     Commencez
    0.54
    PDO
    0.54
     PDO
    0.54
    THISDAY
    0.53
    Prepared
    0.50
    Activations Density 0.066%

    No Known Activations