© 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. 98031
    Prev
    Next
    INDEX
    Explanations

    is

    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
     AssemblyCulture
    -0.88
    تقاوى
    -0.75
    oredCriteria
    -0.60
    "):
    -0.59
     oorspron
    -0.58
    LookAnd
    -0.58
    mergeFrom
    -0.57
     supérieures
    -0.57
    RegressionTest
    -0.56
    قایناق‌لار
    -0.56
    POSITIVE LOGITS
     it
    0.70
     its
    0.69
     that
    0.54
     how
    0.52
     Justicia
    0.51
    它的
    0.49
    pace
    0.49
    its
    0.48
     dass
    0.47
    zeugung
    0.47
    Activations Density 0.006%

    No Known Activations