© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2604
    Prev
    Next
    INDEX
    Explanations

    in

    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
    RenderAtEndOf
    -0.65
    makeConstraints
    -0.56
     ffilmiau
    -0.55
     }}"
    -0.54
    __":
    -0.52
     insuffisamment
    -0.52
    AutoScale
    -0.51
    ]")]
    -0.51
    ini
    -0.50
    StreetMap
    -0.49
    POSITIVE LOGITS
    OGND
    0.57
     itſelf
    0.54
    +#+
    0.54
     kasarigan
    0.52
    IonicModule
    0.50
     visitor
    0.49
    ècie
    0.48
     WebDriverWait
    0.47
     Shane
    0.46
     المتح
    0.46
    Activations Density 0.002%

    No Known Activations