© 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. 91346
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ValueStyle
    -1.05
     CreateTagHelper
    -1.01
     themſelves
    -0.91
    AddTagHelper
    -0.89
     препратки
    -0.85
     itſelf
    -0.84
    ISupport
    -0.83
    ]--;
    -0.82
     poffe
    -0.81
    évaluateur
    -0.80
    POSITIVE LOGITS
     to
    0.83
     by
    0.82
     with
    0.61
     make
    0.60
     distribute
    0.59
     add
    0.57
     calculate
    0.57
     ensure
    0.56
     expose
    0.56
     introduce
    0.56
    Activations Density 0.002%

    No Known Activations