© 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. 4-CLT-HP
    7. 199
    Prev
    Next
    INDEX
    Explanations

    identity and relationships

    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
     my
    -0.56
    ramine
    -0.51
    StoreMessageInfo
    -0.51
    WebServlet
    -0.48
    rofl
    -0.47
     Schein
    -0.46
    <![
    -0.46
     cầu
    -0.45
    ordnet
    -0.45
     mein
    -0.43
    POSITIVE LOGITS
    enumi
    0.69
     برانيه
    0.65
     themselves
    0.62
     AssemblyTitle
    0.59
    theless
    0.58
    MessageTagHelper
    0.58
    vē
    0.56
     herself
    0.55
     متعلقه
    0.54
    !*\
    0.52
    Activations Density 0.045%

    No Known Activations