© 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. 3457
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    bootstrapcdn
    -0.83
     Мексичка
    -0.83
    andExpect
    -0.68
    клопе
    -0.64
    RenderAtEndOf
    -0.62
     Italijanski
    -0.61
    Vidite
    -0.59
    CodedInputStream
    -0.59
    出版年
    -0.59
    lapsingToolbar
    -0.59
    POSITIVE LOGITS
     like
    0.54
    .
    0.53
     for
    0.50
    afficheront
    0.50
    ardless
    0.50
     (
    0.49
    Role
    0.48
    :
    0.48
    ,
    0.46
     esternos
    0.46
    Activations Density 0.019%

    No Known Activations