© 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. 5-CLT-HP
    7. 95221
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    __(/*!
    -0.85
    Gambas
    -0.74
     محفوظة
    -0.71
    økt
    -0.68
    WebVitals
    -0.68
     invokingState
    -0.66
    Collegamenti
    -0.66
    QMetaType
    -0.66
     ostavi
    -0.65
    MLLoader
    -0.61
    POSITIVE LOGITS
     often
    0.66
     already
    0.64
     generally
    0.57
    already
    0.51
    libft
    0.50
     typically
    0.48
     constituted
    0.47
     usually
    0.46
     historically
    0.46
     tend
    0.46
    Activations Density 0.000%

    No Known Activations