© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5677
    Prev
    Next
    INDEX
    Explanations

    copyright/licenses

    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
    ]")]
    -0.52
    urtstag
    -0.51
    visiae
    -0.49
    httphttps
    -0.49
     getchar
    -0.48
    .},
    -0.48
    ]**
    -0.47
     resourceCulture
    -0.47
    ))))))))
    -0.47
     ghetto
    -0.46
    POSITIVE LOGITS
     Wealth
    0.60
     Advisors
    0.59
     Capital
    0.59
     juridiques
    0.56
     régle
    0.56
     Financial
    0.56
     Strategies
    0.55
     Credit
    0.54
    AndEndTag
    0.54
     Learning
    0.54
    Activations Density 0.007%

    No Known Activations