© 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. 1-CLT-HP
    7. 12351
    Prev
    Next
    INDEX
    Explanations

    formation or creation (verb)

    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
    Londres
    -0.51
    Хьажоргаш
    -0.50
    pertino
    -0.50
     AttributeSet
    -0.49
    lichkeiten
    -0.48
    klere
    -0.47
    checkable
    -0.47
    かしい
    -0.47
     않았
    -0.46
    áfrica
    -0.46
    POSITIVE LOGITS
     by
    1.02
     from
    0.81
    by
    0.60
     through
    0.60
    Datuak
    0.59
    Décès
    0.58
     using
    0.57
     about
    0.57
     with
    0.56
     thereby
    0.56
    Activations Density 0.023%

    No Known Activations