© 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. 0-CLT-HP
    7. 95062
    Prev
    Next
    INDEX
    Explanations

    possibility or ability

    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
     démocr
    -0.77
     étrangères
    -0.71
     humaine
    -0.69
     fédé
    -0.69
     feroit
    -0.68
     étoit
    -0.67
     commerciaux
    -0.67
     religieuse
    -0.66
     médicale
    -0.66
     termica
    -0.66
    POSITIVE LOGITS
    Personendaten
    0.84
     find
    0.82
     see
    0.80
     think
    0.75
     choose
    0.73
     get
    0.71
     select
    0.71
     AssemblyTitle
    0.70
     ſind
    0.69
     obtain
    0.68
    Activations Density 0.124%

    No Known Activations