© 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. 5-CLT-HP
    7. 4178
    Prev
    Next
    INDEX
    Explanations

    Locations/directions

    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
     reden
    -0.48
     sola
    -0.47
     PyTuple
    -0.46
     Paglinawan
    -0.43
    edd
    -0.42
     Least
    -0.41
    ezers
    -0.41
    Least
    -0.40
    ]<<
    -0.40
     least
    -0.40
    POSITIVE LOGITS
    rungsseite
    0.96
    ScopeManager
    0.70
    ttino
    0.66
    Viited
    0.64
    onViewCreated
    0.63
     cref
    0.60
     resourceCulture
    0.57
    TagMode
    0.57
     ***!
    0.56
    verwijspagina
    0.56
    Activations Density 0.001%

    No Known Activations