Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95331
    Prev
    Next
    INDEX
    Explanations

    background

    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
    queryInterface
    -0.61
    :✨
    -0.59
    WebElementEntity
    -0.58
     kasarigan
    -0.56
     "..\..\
    -0.53
     дописавши
    -0.53
     lenker
    -0.52
    AndEndTag
    -0.51
     Италијани
    -0.50
    Datuak
    -0.50
    POSITIVE LOGITS
    }
    0.85
    ]
    0.85
    ](#
    0.84
    .}\
    0.82
    ):}
    0.81
    '')
    0.81
    ’)
    0.79
    )
    0.79
    ?]
    0.79
    ?}
    0.78
    Activations Density 0.124%

    No Known Activations