© 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. 0-CLT-HP
    7. 42562
    Prev
    Next
    INDEX
    Explanations

    purification

    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
     purification
    -1.05
     purifying
    -1.00
     purify
    -0.99
     purified
    -0.91
    puri
    -0.88
     Purification
    -0.83
     purity
    -0.81
     Purity
    -0.79
    AndEndTag
    -0.77
     ModelExpression
    -0.76
    POSITIVE LOGITS
    s
    0.73
    nloa
    0.55
    ring
    0.54
    send
    0.52
    sol
    0.51
    nuts
    0.49
    ing
    0.48
    serv
    0.48
    cred
    0.48
    sling
    0.47
    Activations Density 1.680%

    No Known Activations