© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43620
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Normdatei
    -0.62
    +:+
    -0.58
     preuves
    -0.57
    };*/
    -0.57
     móveis
    -0.57
    manteau
    -0.57
    >-->
    -0.56
     consommateurs
    -0.55
     oreilles
    -0.54
     dépenses
    -0.54
    POSITIVE LOGITS
    0
    0.70
     days
    0.63
     Uff
    0.59
    ########.
    0.59
    zero
    0.59
    ZERO
    0.57
     huts
    0.56
     metres
    0.55
     meters
    0.55
     ligiloj
    0.55
    Activations Density 0.575%

    No Known Activations