© 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. 20-CLT-HP
    7. 72675
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
    MarshalTo
    -0.71
     ujednoznacz
    -0.70
     الرياضيه
    -0.69
    #+#
    -0.67
     Legendre
    -0.66
     alts
    -0.64
     الحره
    -0.63
    VIAF
    -0.62
    /**
    -0.60
     Préférences
    -0.60
    POSITIVE LOGITS
    UpInside
    0.43
     linkovi
    0.42
    母
    0.41
     Ana
    0.41
    pearing
    0.40
     triliun
    0.40
     هيا
    0.40
     Recursos
    0.40
     pa
    0.39
    rspec
    0.39
    Activations Density 0.000%

    No Known Activations