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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96395
    Prev
    Next
    INDEX
    Explanations

    features

    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
    '],
    -0.50
    ètement
    -0.48
    Rptr
    -0.47
     Spisak
    -0.47
     investment
    -0.47
    /**
    -0.46
    -------
    -0.46
     separations
    -0.46
     periods
    -0.45
     fidelity
    -0.45
    POSITIVE LOGITS
     '\\;'
    0.62
    +:+
    0.58
    OGND
    0.58
    PerformLayout
    0.58
    parsedMessage
    0.57
     run
    0.56
    Zeneca
    0.56
    exitRule
    0.54
    copg
    0.54
    findpost
    0.53
    Activations Density 0.007%

    No Known Activations