© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97472
    Prev
    Next
    INDEX
    Explanations

    product

    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
    ViewFeatures
    -0.86
    
    -0.82
    Portale
    -0.80
    ]--;
    -0.75
     الحره
    -0.73
    NUMX
    -0.70
    ).__
    -0.68
    !")
    
    -0.67
    theless
    -0.66
    ITERATURE
    -0.66
    POSITIVE LOGITS
     and
    0.62
    #+#
    0.60
    apimachinery
    0.49
     that
    0.47
     like
    0.47
    BA
    0.41
     for
    0.41
     such
    0.40
     at
    0.40
     -
    0.40
    Activations Density 0.027%

    No Known Activations