© 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. 1479
    Prev
    Next
    INDEX
    Explanations

    Bullet points

    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
     nakalista
    -1.05
    findpost
    -0.81
     виправивши
    -0.81
    出版年
    -0.78
    writeField
    -0.74
    \{\\
    -0.74
     typelib
    -0.74
    DebuggerNonUser
    -0.73
     AssemblyProduct
    -0.70
    ՚
    -0.66
    POSITIVE LOGITS
    1
    0.44
     exists
    0.43
     strong
    0.43
    niająca
    0.42
     existir
    0.42
    zeitig
    0.41
    ↵
    0.40
      
    0.39
     exist
    0.39
     a
    0.38
    Activations Density 0.005%

    No Known Activations