© 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. 14577
    Prev
    Next
    INDEX
    Explanations

    stability

    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
     Stability
    -0.99
    Stability
    -0.96
     stability
    -0.88
     STABILITY
    -0.81
    ContentAlignment
    -0.81
    IVEREF
    -0.81
     instability
    -0.80
    stability
    -0.80
     candidates
    -0.75
     Instability
    -0.74
    POSITIVE LOGITS
     margin
    0.50
     Motta
    0.47
     rendering
    0.47
     mechanisms
    0.47
     render
    0.46
     Mechanisms
    0.46
     margins
    0.45
     Mechanism
    0.44
     newData
    0.44
     mechanism
    0.44
    Activations Density 0.090%

    No Known Activations