© 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. 5-CLT-HP
    7. 4695
    Prev
    Next
    INDEX
    Explanations

    many

    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
    yntaxException
    -0.61
    more
    -0.60
    More
    -0.57
     more
    -0.57
    Demografia
    -0.52
    different
    -0.52
    più
    -0.52
     More
    -0.51
    μως
    -0.49
    Biblia
    -0.49
    POSITIVE LOGITS
     boî
    0.57
    }),
    0.57
     useAppContext
    0.57
    )}}{
    0.57
     expectation
    0.57
    ')->
    0.57
     wissen
    0.57
     Waray
    0.57
    })->
    0.56
    ]),
    0.56
    Activations Density 0.002%

    No Known Activations