© 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. 1486
    Prev
    Next
    INDEX
    Explanations

    like

    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
     these
    -1.54
    these
    -1.40
    These
    -1.34
     These
    -1.24
     THESE
    -1.14
     thefe
    -1.14
    Estos
    -1.08
     theſe
    -1.04
    这些
    -1.03
    這些
    -1.02
    POSITIVE LOGITS
     surla
    0.54
    goes
    0.53
     that
    0.50
     Says
    0.49
     Wants
    0.49
    Kontrola
    0.48
    GEBURTSDATUM
    0.47
    SharedDtor
    0.47
    WithIdentifier
    0.47
    uxxxx
    0.47
    Activations Density 0.003%

    No Known Activations