© 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. 42881
    Prev
    Next
    INDEX
    Explanations

    legal, law

    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
     Nightingale
    -1.12
    ILogger
    -0.68
     Fargo
    -0.62
    Hrsg
    -0.62
     estekak
    -0.60
    RegressionTest
    -0.59
    [](
    -0.58
    ритори
    -0.57
    expandindo
    -0.56
    __':
    -0.56
    POSITIVE LOGITS
     Normdatei
    0.53
     <=",
    0.47
    hdashline
    0.44
    UnusedPrivate
    0.43
    ıç
    0.43
    下载附件
    0.42
     occasione
    0.41
    verständlich
    0.41
     Dest
    0.41
    ISSE
    0.41
    Activations Density 2.593%

    No Known Activations