© 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. 5-CLT-HP
    7. 3343
    Prev
    Next
    INDEX
    Explanations

    limiting statements

    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
     have
    -0.42
     a
    -0.40
    这是一个
    -0.39
     hän
    -0.39
    国
    -0.38
    一个
    -0.37
     ļ
    -0.37
    refreshToken
    -0.37
     an
    -0.36
    einem
    -0.36
    POSITIVE LOGITS
     AssemblyCulture
    0.99
    expandindo
    0.98
    ReusableCell
    0.96
     autorytatywna
    0.95
    MemoryWarning
    0.94
    Portale
    0.92
    SourceChecksum
    0.85
    PerformLayout
    0.84
    principalColumn
    0.84
    EndInit
    0.82
    Activations Density 0.002%

    No Known Activations