© 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. 42743
    Prev
    Next
    INDEX
    Explanations

    Welcome

    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
    Imagine
    -0.87
     Imagine
    -0.80
     imagine
    -0.77
    Jereo
    -0.69
     köln
    -0.63
    writeFieldEnd
    -0.63
    AndEndTag
    -0.62
     calendriers
    -0.61
     Juifs
    -0.61
    GEBURTSDATUM
    -0.61
    POSITIVE LOGITS
    ględ
    0.50
     Nor
    0.49
    !*\
    0.48
    GUILayout
    0.48
    Vidite
    0.45
    ysław
    0.45
     ja
    0.44
    ja
    0.44
    chaft
    0.43
    TOGGLE
    0.43
    Activations Density 0.169%

    No Known Activations