© 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. 42289
    Prev
    Next
    INDEX
    Explanations

    of

    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
     "'");
    -0.59
    |}{\
    -0.52
    LookAnd
    -0.51
    ódź
    -0.50
    )";
    -0.49
    makeText
    -0.47
     lợi
    -0.46
    ্ষ
    -0.46
    Kjelder
    -0.46
     Lati
    -0.46
    POSITIVE LOGITS
    CloseOperation
    0.71
    DispatchToProps
    0.58
     NUKAT
    0.58
     Datenschutzer
    0.57
    reportWebVitals
    0.57
    tető
    0.55
    PrivateRoute
    0.54
    Scénario
    0.53
     rencontr
    0.53
     himo
    0.52
    Activations Density 0.266%

    No Known Activations