© 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. 39794
    Prev
    Next
    INDEX
    Explanations

    nominally

    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
     nominally
    -0.72
    XtraEditors
    -0.71
    aarrggbb
    -0.69
    DockStyle
    -0.65
    InputBorder
    -0.63
    UnitTesting
    -0.62
    sizeCache
    -0.61
    UrlResolution
    -0.61
     careers
    -0.59
     سكانية
    -0.59
    POSITIVE LOGITS
    s
    0.67
    urally
    0.49
    kyou
    0.48
    ів
    0.47
    atherapy
    0.46
     pylori
    0.46
    ی
    0.45
    space
    0.45
    sstelle
    0.45
    GHIJKLM
    0.45
    Activations Density 0.087%

    No Known Activations