© 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. 93163
    Prev
    Next
    INDEX
    Explanations

    best

    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
     best
    -1.28
    best
    -0.88
     Best
    -0.87
    Best
    -0.81
     beste
    -0.80
     melhor
    -0.73
     mejor
    -0.71
     meilleur
    -0.67
     BEST
    -0.67
    BEST
    -0.64
    POSITIVE LOGITS
    ########.
    0.96
     wives
    0.77
     executions
    0.77
     raiſ
    0.73
    +#+#
    0.72
     "..\..\..\
    0.70
     tails
    0.68
     ſta
    0.68
    homonymie
    0.67
     ſtate
    0.67
    Activations Density 0.165%

    No Known Activations