© 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. 42361
    Prev
    Next
    INDEX
    Explanations

    adrenaline

    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
    rad
    -0.81
    tide
    -0.65
    ride
    -0.60
     ainfi
    -0.60
     Anſ
    -0.59
    Extent
    -0.58
    bud
    -0.58
     sibi
    -0.57
    出版年
    -0.57
     ſche
    -0.56
    POSITIVE LOGITS
    twimg
    0.65
    audiovisuel
    0.64
    HasForeignKey
    0.63
    endphp
    0.52
    runApp
    0.52
    tku
    0.51
    Activités
    0.50
    PhysRevLett
    0.50
     amen
    0.50
    usepackage
    0.50
    Activations Density 1.563%

    No Known Activations