© 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. 98022
    Prev
    Next
    INDEX
    Explanations

    chemicals and pollution

    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
    inSlope
    -0.45
     kasarigan
    -0.44
    thys
    -0.42
    writeHead
    -0.40
    hwar
    -0.39
     mené
    -0.39
    ReusableCell
    -0.38
     xl
    -0.38
    τως
    -0.38
     HasFactory
    -0.37
    POSITIVE LOGITS
     <=",
    0.78
     noqa
    0.68
     صوتيه
    0.62
    verifyException
    0.59
     italienne
    0.59
    XmlAccessType
    0.56
    elemField
    0.56
    DoubleQuotes
    0.55
     خارجية
    0.55
    KURZBESCHREIBUNG
    0.55
    Activations Density 0.010%

    No Known Activations