© 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. 95084
    Prev
    Next
    INDEX
    Explanations

    code or technical content

    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
    reportWebVitals
    -0.72
     <=",
    -0.71
    Chham
    -0.62
    mybatisplus
    -0.61
    dafx
    -0.59
    adaptiveStyles
    -0.58
     Paglinawan
    -0.56
    %";
    -0.56
    featureID
    -0.54
    orianCalendar
    -0.54
    POSITIVE LOGITS
     Weltkrieg
    0.54
     suspended
    0.49
    tila
    0.49
     Suspended
    0.48
    crisy
    0.48
     kraj
    0.47
    Suspended
    0.47
    Known
    0.47
    unk
    0.47
     suspen
    0.47
    Activations Density 0.001%

    No Known Activations