© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1917
    Prev
    Next
    INDEX
    Explanations

    Code and data

    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
     Timeline
    -0.50
     movement
    -0.48
     movements
    -0.47
    Conor
    -0.47
    gh
    -0.46
    ca
    -0.46
     timeline
    -0.45
     ap
    -0.45
     Dollar
    -0.44
    ◄
    -0.44
    POSITIVE LOGITS
    MemoryWarning
    0.65
    InjectMocks
    0.63
     AssemblyCulture
    0.63
    PerformLayout
    0.61
     препратки
    0.60
     referenties
    0.58
    IsContent
    0.56
    RefNanny
    0.56
     يتيمه
    0.55
    fjspx
    0.55
    Activations Density 0.008%

    No Known Activations