© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41894
    Prev
    Next
    INDEX
    Explanations

    mathematics or space

    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
     blessés
    -0.68
     fausse
    -0.68
    #+#
    -0.63
     FishBase
    -0.61
     vœux
    -0.60
    Revenir
    -0.60
    ïsme
    -0.60
    saraba
    -0.60
     grève
    -0.60
     attentes
    -0.59
    POSITIVE LOGITS
     AssemblyCulture
    0.54
     required
    0.50
     material
    0.50
     species
    0.48
    s
    0.47
     frame
    0.47
    .
    0.47
     properties
    0.46
     Tim
    0.45
    Tim
    0.45
    Activations Density 0.071%

    No Known Activations