© 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. 0-CLT-HP
    7. 41113
    Prev
    Next
    INDEX
    Explanations

    bracket

    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
     on
    -1.05
     On
    -0.83
    On
    -0.71
     ON
    -0.57
     trên
    -0.52
    SharedCtor
    -0.50
     på
    -0.49
    OnItem
    -0.48
    insee
    -0.47
    省市镇
    -0.47
    POSITIVE LOGITS
     Theſe
    0.77
     FormData
    0.70
     Majefty
    0.69
     Monfieur
    0.67
    IntoConstraints
    0.66
    ########.
    0.65
    #+#
    0.64
     Houſe
    0.64
     cref
    0.63
    SBATCH
    0.63
    Activations Density 1.518%

    No Known Activations