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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 398
    Prev
    Next
    INDEX
    Explanations

    system

    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
    ValueStyle
    -0.82
    期刊论文
    -0.73
     propOrder
    -0.68
    queryInterface
    -0.66
    }));
    -0.64
     AssemblyProduct
    -0.62
     Normdatei
    -0.62
    OGND
    -0.60
    ]));
    -0.57
    PreferredItem
    -0.56
    POSITIVE LOGITS
    ATTENTION
    0.52
    Attention
    0.51
    AddField
    0.50
     Attention
    0.49
     magasiner
    0.49
    Française
    0.48
     ATTENTION
    0.48
    orited
    0.47
     Ansatz
    0.43
    那
    0.43
    Activations Density 0.008%

    No Known Activations