© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95674
    Prev
    Next
    INDEX
    Explanations

    )

    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
    Negative Logits
     EconPapers
    -0.99
     ujednoznacz
    -0.93
    SBATCH
    -0.88
    tvguidetime
    -0.88
     tartalomajánló
    -0.86
     تضيفلها
    -0.84
    IsContent
    -0.84
    verwijspagina
    -0.84
    ValueStyle
    -0.83
     saites
    -0.81
    POSITIVE LOGITS
     Cour
    0.53
    "
    0.52
     "
    0.52
     Plan
    0.51
     
    0.49
    .
    0.49
    Cour
    0.47
    ,
    0.47
     cour
    0.45
    '
    0.45
    Activations Density 0.254%

    No Known Activations