© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2208
    Prev
    Next
    INDEX
    Explanations

    cid

    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
     AssemblyCompany
    -0.62
     sonora
    -0.62
     дописавши
    -0.61
    HttpPut
    -0.61
    contentLoaded
    -0.56
     Adult
    -0.55
    Adult
    -0.54
     estekak
    -0.54
    NewRow
    -0.53
    ValueGeneration
    -0.51
    POSITIVE LOGITS
    XmlAccessorType
    0.53
    hawar
    0.53
    antMatchers
    0.50
     jLabel
    0.50
    AddAttribute
    0.48
    HomeAsUpEnabled
    0.47
    جغرافيا
    0.47
    +(-
    0.46
    MeasureSpec
    0.46
     defaultstate
    0.46
    Activations Density 0.002%

    No Known Activations