© 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. 0-CLT-HP
    7. 94398
    Prev
    Next
    INDEX
    Explanations

    Events, news, opinions

    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
    +#+#
    -0.85
     AssemblyProduct
    -0.84
     ProtoMessage
    -0.83
    TintMode
    -0.82
     виправивши
    -0.81
    messageInfo
    -0.79
     <=",
    -0.67
     MenuView
    -0.67
    fjspx
    -0.66
    Datuak
    -0.65
    POSITIVE LOGITS
    〉
    0.44
     gi
    0.42
    HideInInspector
    0.42
    tec
    0.41
    toggler
    0.40
    СТО
    0.39
    pannt
    0.39
    bek
    0.39
     ali
    0.38
     sav
    0.38
    Activations Density 1.655%

    No Known Activations