© 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. 4-CLT-HP
    7. 2334
    Prev
    Next
    INDEX
    Explanations

    it

    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
    ValueGenerated
    -0.54
     getItemId
    -0.53
    tigma
    -0.52
    (!__
    -0.50
    tanooga
    -0.48
    LEncoder
    -0.47
    set
    -0.47
     Logement
    -0.47
    global
    -0.46
     InputDecoration
    -0.46
    POSITIVE LOGITS
    énario
    0.56
     estekak
    0.52
    €)
    0.50
     AUSSI
    0.49
    ]')
    0.49
    csol
    0.48
     inevitable
    0.47
    }))
    0.47
    gham
    0.47
    zboi
    0.45
    Activations Density 0.003%

    No Known Activations