© 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. 14645
    Prev
    Next
    INDEX
    Explanations

    sorely

    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
    omeness
    -0.94
    featureID
    -0.91
    IntoConstraints
    -0.88
    migrationBuilder
    -0.86
    ness
    -0.82
    ingly
    -0.81
     MonoBehaviour
    -0.81
    Personendaten
    -0.80
    exitRule
    -0.79
    AccessorTable
    -0.78
    POSITIVE LOGITS
     
    0.51
     practical
    0.35
     bu
    0.35
     ,
    0.34
     st
    0.33
     sometimes
    0.32
     apparent
    0.32
    前进
    0.32
    </b>
    0.32
    </strong>
    0.32
    Activations Density 0.010%

    No Known Activations