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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92151
    Prev
    Next
    INDEX
    Explanations

    eam

    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
     fubject
    -0.85
     pleaſure
    -0.84
     poffible
    -0.80
     poffe
    -0.79
     chofe
    -0.78
     uſed
    -0.77
     للمعارف
    -0.75
    ########.
    -0.74
     Jefus
    -0.73
     Theſe
    -0.73
    POSITIVE LOGITS
    ly
    0.61
    s
    0.54
    lik
    0.54
    CodeAttribute
    0.54
    mod
    0.52
    mi
    0.50
    mos
    0.49
     U
    0.48
    my
    0.47
    mey
    0.47
    Activations Density 0.252%

    No Known Activations