© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3334
    Prev
    Next
    INDEX
    Explanations

    access

    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
     AssemblyCulture
    -0.65
    InjectAttribute
    -0.65
    <bos>
    -0.65
    moine
    -0.64
    contentLoaded
    -0.63
     enví
    -0.56
     BrowserModule
    -0.56
     propOrder
    -0.55
    exitRule
    -0.54
    You
    -0.53
    POSITIVE LOGITS
     tons
    0.79
     our
    0.79
     great
    0.68
     top
    0.68
     thousands
    0.66
    ')}}"
    0.60
     hundreds
    0.59
     over
    0.59
     a
    0.57
     awesome
    0.57
    Activations Density 0.002%

    No Known Activations