© 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. 98165
    Prev
    Next
    INDEX
    Explanations

    I

    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
    principalTable
    -0.54
     يتيمه
    -0.54
    abestanden
    -0.50
    Халык
    -0.50
     buono
    -0.49
     råd
    -0.48
     filling
    -0.47
     building
    -0.47
     rebuilding
    -0.47
     feeding
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.61
     OFDb
    0.54
    InitVars
    0.54
     as
    0.53
    hnia
    0.52
     المعيارى
    0.52
    FunctionFlags
    0.51
    erals
    0.50
    matum
    0.50
    paravant
    0.49
    Activations Density 0.001%

    No Known Activations