© 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. 4579
    Prev
    Next
    INDEX
    Explanations

    formal written language

    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
    EndTag
    -0.68
    cknow
    -0.67
     avoient
    -0.60
    archiviato
    -0.58
     Chriftian
    -0.57
    chiali
    -0.56
    ękuję
    -0.54
     betweenstory
    -0.54
     الاطلاع
    -0.54
     kasarigan
    -0.54
    POSITIVE LOGITS
    gouv
    0.60
    npmjs
    0.51
     transfieras
    0.50
    monde
    0.48
    XDECREF
    0.47
    <?
    0.46
    lotte
    0.46
     combat
    0.45
    fiore
    0.45
    béco
    0.45
    Activations Density 0.001%

    No Known Activations