© 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. 1271
    Prev
    Next
    INDEX
    Explanations

    code

    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
     transférez
    -0.70
    SharedDtor
    -0.58
    featureID
    -0.57
     immor
    -0.57
    Initializable
    -0.54
    flare
    -0.51
    makeConstraints
    -0.51
    cemia
    -0.50
    lccn
    -0.50
    ########.
    -0.49
    POSITIVE LOGITS
    OrBuilder
    0.60
     hwnd
    0.55
    InjectMocks
    0.51
    əri
    0.50
     soigne
    0.50
    Amour
    0.50
    hammed
    0.49
    .*")]
    0.49
     Process
    0.48
    yorsunuz
    0.48
    Activations Density 0.001%

    No Known Activations