© 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. 1-CLT-HP
    7. 14507
    Prev
    Next
    INDEX
    Explanations

    roid and perpendicular

    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
    roid
    -1.01
    ROID
    -0.93
    roids
    -0.92
     MonoBehaviour
    -0.79
    enderror
    -0.76
    AndEndTag
    -0.73
    ]--;
    -0.71
     StatefulWidget
    -0.71
     StatelessWidget
    -0.66
    voort
    -0.65
    POSITIVE LOGITS
    ly
    0.52
    ivät
    0.47
    lye
    0.42
    osamente
    0.42
    iously
    0.42
    ity
    0.42
    ily
    0.41
    voyer
    0.41
    s
    0.40
    linking
    0.39
    Activations Density 0.018%

    No Known Activations