© 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. 92308
    Prev
    Next
    INDEX
    Explanations

    state

    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
    WebControls
    -0.54
    icina
    -0.47
     awa
    -0.46
     the
    -0.46
    ite
    -0.45
    fant
    -0.45
     establishment
    -0.43
     on
    -0.43
     Messiah
    -0.43
    iani
    -0.43
    POSITIVE LOGITS
    AndEndTag
    1.12
    yntaxException
    0.87
    amaño
    0.73
    ftagPool
    0.72
    TagMode
    0.71
    IUrlHelper
    0.71
     compréhen
    0.62
     Normdatei
    0.60
    GEBURTS
    0.60
     AssemblyTitle
    0.58
    Activations Density 0.001%

    No Known Activations