© 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. 95618
    Prev
    Next
    INDEX
    Explanations

    most

    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
     most
    -0.81
    finally
    -0.43
     finally
    -0.42
    alate
    -0.42
    [toxicity=0]
    -0.42
    acij
    -0.41
    Most
    -0.40
    most
    -0.40
    неопр
    -0.39
     more
    -0.39
    POSITIVE LOGITS
     specialises
    0.71
     recognises
    0.70
     owes
    0.68
    CloseOperation
    0.66
    numerusform
    0.66
     conforms
    0.65
     inherits
    0.65
    :✨
    0.64
     understands
    0.64
     TextFormField
    0.63
    Activations Density 0.072%

    No Known Activations