© 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. 5-CLT-HP
    7. 93176
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     '\\;'
    -0.93
    GEBURTSDATUM
    -0.86
     kaarangay
    -0.77
    }],
    -0.72
     propOrder
    -0.71
    }]
    -0.71
    ineno
    -0.70
    帖最后由
    -0.68
     resourceCulture
    -0.68
    HomeAsUpEnabled
    -0.68
    POSITIVE LOGITS
     how
    0.59
     the
    0.56
    that
    0.52
     that
    0.50
    how
    0.48
     fusca
    0.47
    יצוני
    0.43
     Brand
    0.42
    zugs
    0.42
    whom
    0.42
    Activations Density 0.002%

    No Known Activations