© 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. 1-CLT-HP
    7. 9595
    Prev
    Next
    INDEX
    Explanations

    programming/technical descriptions

    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
    MessageTagHelper
    -0.72
     صوتيه
    -0.70
    цездатний
    -0.66
    tagHelper
    -0.63
     démocratie
    -0.60
     esternos
    -0.60
     prototype
    -0.59
     econó
    -0.58
    AntiForgeryToken
    -0.58
     nød
    -0.57
    POSITIVE LOGITS
    ])));
    0.52
    withstanding
    0.50
    ))))))))
    0.49
    AutoresizingMask
    0.49
    InjectMocks
    0.48
    GenerationType
    0.45
     Dir
    0.45
    oje
    0.45
    )");
    0.44
    inite
    0.44
    Activations Density 0.015%

    No Known Activations