© 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. 1-CLT-HP
    7. 15571
    Prev
    Next
    INDEX
    Explanations

    some

    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
     some
    -1.20
     Some
    -1.12
    some
    -1.10
    Some
    -1.05
    Algunos
    -0.96
    RegistryLite
    -0.92
     SOME
    -0.91
    SOME
    -0.90
    Algunas
    -0.87
     Algunos
    -0.86
    POSITIVE LOGITS
     is
    0.63
     are
    0.62
     prêtres
    0.53
     vœux
    0.51
    =");
    0.49
     can
    0.48
    seamnă
    0.47
     means
    0.46
     aikana
    0.46
     preuves
    0.46
    Activations Density 0.138%

    No Known Activations