© 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. 4594
    Prev
    Next
    INDEX
    Explanations

    Names and company emails

    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
     поводу
    -0.45
     mailed
    -0.45
     mail
    -0.41
     situación
    -0.41
    oló
    -0.41
     posibil
    -0.40
     maaaring
    -0.38
    anjutan
    -0.38
    ณี
    -0.38
    Dear
    -0.38
    POSITIVE LOGITS
     שוליים
    0.77
    mergeFrom
    0.71
     հղումներ
    0.70
    Portale
    0.69
     &___
    0.68
    queryInterface
    0.67
    setViewportView
    0.67
     Throwable
    0.66
    VIAF
    0.66
    Personensuche
    0.63
    Activations Density 0.017%

    No Known Activations