© 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. 4-CLT-HP
    7. 480
    Prev
    Next
    INDEX
    Explanations

    code, HTML

    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
     Puoi
    -0.61
    MathML
    -0.58
    ones
    -0.56
     Siamo
    -0.56
    culares
    -0.56
     Abbiamo
    -0.50
    utives
    -0.49
    rous
    -0.49
     ourselves
    -0.49
     whereof
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.71
     &___
    0.70
    NOPQRST
    0.63
     AssemblyCompany
    0.61
     समीक्षाओं
    0.60
    WithIOException
    0.59
    aisons
    0.54
    OGND
    0.54
    tehen
    0.54
     fabricants
    0.53
    Activations Density 0.001%

    No Known Activations