© 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. 90930
    Prev
    Next
    INDEX
    Explanations

    investments and finance

    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
    ree
    -0.83
    REE
    -0.74
     unfolding
    -0.72
     unfolded
    -0.71
    ItemBackground
    -0.71
    ViewImports
    -0.69
     становника
    -0.65
     unfold
    -0.65
    ruptedException
    -0.63
     investments
    -0.63
    POSITIVE LOGITS
    astify
    0.48
    MOH
    0.47
    esterno
    0.46
     épu
    0.46
    tria
    0.44
    Véxase
    0.44
    Ƭ
    0.44
     sī
    0.44
    bleed
    0.43
    IGAN
    0.42
    Activations Density 1.494%

    No Known Activations