© 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. 98049
    Prev
    Next
    INDEX
    Explanations

    counter arguments

    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
     igång
    -0.83
    FunctionFlags
    -0.82
     ―――――
    -0.79
     initComponents
    -0.78
    rungsseite
    -0.78
    UnusedPrivate
    -0.78
    XmlAccessType
    -0.77
     utafitiHapana
    -0.77
     الحره
    -0.76
     stället
    -0.75
    POSITIVE LOGITS
     and
    1.02
    ,
    0.57
     those
    0.56
     it
    0.52
     the
    0.51
     a
    0.50
    DispatchToProps
    0.42
     to
    0.42
     his
    0.41
     mo
    0.41
    Activations Density 0.002%

    No Known Activations