© 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. 1-CLT-HP
    7. 10502
    Prev
    Next
    INDEX
    Explanations

    subjective language

    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
    hintText
    -0.43
    ↵
    -0.42
    </td>
    -0.42
     tr
    -0.41
    </code>
    -0.41
    ↵↵↵↵↵
    -0.41
    ${
    -0.40
     multiprocessing
    -0.40
    ↵↵↵↵↵↵↵
    -0.40
    Facades
    -0.39
    POSITIVE LOGITS
    ValueStyle
    1.03
    tagHelperRunner
    0.98
     Савезне
    0.89
    MLLoader
    0.85
    complexContent
    0.83
    ſelf
    0.81
     pinulongan
    0.80
    Personendaten
    0.80
    PerformLayout
    0.76
    @[+][
    0.75
    Activations Density 0.005%

    No Known Activations