© 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. 5410
    Prev
    Next
    INDEX
    Explanations

    period

    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
    WithIOException
    -0.81
    SourceChecksum
    -0.77
     Roskov
    -0.69
    GEBURTSDATUM
    -0.69
     propOrder
    -0.66
    enterOuterAlt
    -0.62
    ViewFeatures
    -0.61
    Vidite
    -0.59
    #
    -0.58
     kaarangay
    -0.57
    POSITIVE LOGITS
     short
    0.49
    uzu
    0.49
    Short
    0.48
    ISO
    0.48
    iso
    0.47
    amar
    0.44
    Hochspringen
    0.44
     like
    0.43
    Ide
    0.43
     union
    0.43
    Activations Density 0.002%

    No Known Activations