© 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. 1-CLT-HP
    7. 9046
    Prev
    Next
    INDEX
    Explanations

    ome

    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
    Personendaten
    -0.89
    تقاوى
    -0.79
     Roskov
    -0.78
     pleaſure
    -0.70
     purpoſe
    -0.70
    +#+#
    -0.69
    FormTagHelper
    -0.68
     متعلقه
    -0.67
     تانيه
    -0.67
    antaranya
    -0.67
    POSITIVE LOGITS
    ("")]
    0.50
     under
    0.45
    </h4>
    0.44
     out
    0.42
     j
    0.41
     copy
    0.41
     end
    0.41
     can
    0.40
     much
    0.40
     qu
    0.40
    Activations Density 0.108%

    No Known Activations