© 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. 4-CLT-HP
    7. 1932
    Prev
    Next
    INDEX
    Explanations

    risk

    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
    resave
    -0.52
     Lande
    -0.47
    ]--;
    -0.45
     Référence
    -0.45
     Scoop
    -0.44
    itemBuilder
    -0.43
    redo
    -0.43
     DBNull
    -0.42
    annotation
    -0.41
     availability
    -0.40
    POSITIVE LOGITS
    Diweddarwch
    0.71
    RegressionTest
    0.69
    UVWXYZ
    0.63
     âmes
    0.61
     mattina
    0.60
     étanche
    0.60
    URLConnection
    0.60
     mattino
    0.60
    tagHelperRunner
    0.59
    VersionUID
    0.58
    Activations Density 0.002%

    No Known Activations