© 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. 5-CLT-HP
    7. 5421
    Prev
    Next
    INDEX
    Explanations

    coag

    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
     ligiloj
    -0.86
     ostavi
    -0.82
    SpringBootTest
    -0.77
    ArgsConstructor
    -0.75
     snippetHide
    -0.75
     propOrder
    -0.72
    lapsingToolbar
    -0.66
     OnTriggerEnter
    -0.65
     Chwiliwch
    -0.65
    scriptcase
    -0.64
    POSITIVE LOGITS
    ze
    0.57
    Vidite
    0.48
    ZE
    0.47
    fns
    0.47
    geli
    0.46
    Ze
    0.45
    談社
    0.45
     esquem
    0.45
    hes
    0.44
     Ches
    0.44
    Activations Density 0.001%

    No Known Activations