© 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. 92795
    Prev
    Next
    INDEX
    Explanations

    scientific/medical research

    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
    RegressionTest
    -0.58
     PyTuple
    -0.55
    UrlEncoded
    -0.54
     intenso
    -0.50
    openConnection
    -0.49
    httphttps
    -0.47
    loem
    -0.46
    NewUrlParser
    -0.46
    DllImport
    -0.46
    upuesto
    -0.45
    POSITIVE LOGITS
    InstrumentedTest
    0.59
    ScopeManager
    0.58
    Билгалдахарш
    0.53
     ddelweddau
    0.53
     insuffisamment
    0.52
    })$}
    0.52
    AxisAlignment
    0.52
    これから
    0.52
    past
    0.51
     Existing
    0.50
    Activations Density 0.017%

    No Known Activations