© 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. 91867
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Hentet
    -0.64
    planned
    -0.58
     planned
    -0.57
    pires
    -0.56
    Planned
    -0.50
     ITIS
    -0.50
     slik
    -0.49
    expected
    -0.49
     geplant
    -0.49
    scheduled
    -0.47
    POSITIVE LOGITS
     just
    1.01
    just
    0.79
     JUST
    0.75
    Just
    0.72
    NameInMap
    0.71
     Just
    0.69
    sizeCache
    0.68
     focus
    0.68
    enumi
    0.65
     merely
    0.63
    Activations Density 0.017%

    No Known Activations