© 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. 1141
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    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
    -0.65
     Gole
    -0.60
    AnchorStyles
    -0.60
     الحره
    -0.60
     postIndex
    -0.59
     AspNetCore
    -0.59
    wpi
    -0.57
    ppincott
    -0.56
    Jep
    -0.53
    keye
    -0.52
    POSITIVE LOGITS
    ta
    0.56
    Tach
    0.49
    bibitem
    0.47
     réfrig
    0.45
    ädig
    0.45
    bev
    0.45
    ventud
    0.45
    igshid
    0.45
    ctive
    0.45
    Източници
    0.45
    Activations Density 0.001%

    No Known Activations