© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93063
    Prev
    Next
    INDEX
    Explanations

    incarceration/sentences

    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
     سكانية
    -0.69
    yntaxException
    -0.67
    URLException
    -0.64
    Vidite
    -0.63
     JpaRepository
    -0.60
    AsUp
    -0.54
     Visser
    -0.54
    rrggbb
    -0.54
     дописавши
    -0.53
    csolódó
    -0.52
    POSITIVE LOGITS
    TagMode
    0.59
     Having
    0.48
    slf
    0.48
    ([],
    0.48
    Having
    0.48
     smtplib
    0.47
     claiming
    0.47
    fjspx
    0.47
    allclose
    0.46
     having
    0.46
    Activations Density 0.009%

    No Known Activations