© 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. 5-CLT-HP
    7. 4641
    Prev
    Next
    INDEX
    Explanations

    went

    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
    ########.
    -0.78
     referrerpolicy
    -0.68
    +#+#
    -0.66
     Lordships
    -0.64
    脚注の使い方
    -0.63
    ?」
    -0.62
    tableFuture
    -0.61
     تانيه
    -0.59
     برانيه
    -0.59
     joaat
    -0.59
    POSITIVE LOGITS
     AssemblyProduct
    0.67
     little
    0.57
    modelBuilder
    0.56
    "}")
    0.55
     none
    0.55
    SharedCtor
    0.52
     neither
    0.52
     this
    0.51
    urlpatterns
    0.51
     both
    0.50
    Activations Density 0.000%

    No Known Activations