© 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. 5-CLT-HP
    7. 5114
    Prev
    Next
    INDEX
    Explanations

    wrote

    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
     the
    -0.71
     information
    -0.53
    CopyWith
    -0.52
     an
    -0.52
     a
    -0.52
     participation
    -0.49
    ULTS
    -0.47
     interest
    -0.47
     guidance
    -0.47
    ffar
    -0.46
    POSITIVE LOGITS
     would
    0.94
    antaranya
    0.92
     takes
    0.88
     could
    0.88
     will
    0.82
     depends
    0.80
     goes
    0.79
     makes
    0.79
     aligns
    0.78
     corresponds
    0.77
    Activations Density 0.001%

    No Known Activations