© 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. 4-CLT-HP
    7. 1554
    Prev
    Next
    INDEX
    Explanations

    predators and victims

    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
    GraphicsUnit
    -0.81
    principalTable
    -0.76
    ValueStyle
    -0.76
    aarrggbb
    -0.76
    featureID
    -0.75
     تضيفلها
    -0.74
     initComponents
    -0.74
     GenerationType
    -0.73
    lccn
    -0.71
    rungsseite
    -0.71
    POSITIVE LOGITS
     Sem
    0.39
    Sem
    0.36
     to
    0.36
     Ber
    0.35
     Carlos
    0.34
    sy
    0.34
    oplasma
    0.33
     boredom
    0.33
    ymal
    0.32
    sigkeit
    0.31
    Activations Density 0.002%

    No Known Activations