© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71351
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    ]--;
    -0.82
    DoubleQuotes
    -0.74
     الحره
    -0.69
    Amicalement
    -0.64
     صوتيه
    -0.64
    mybatisplus
    -0.64
    )"),
    -0.63
    tagHelperRunner
    -0.63
     resourceCulture
    -0.62
    }}}
    -0.62
    POSITIVE LOGITS
     in
    0.50
     on
    0.49
     within
    0.45
     into
    0.43
     popular
    0.43
     amicable
    0.41
     sans
    0.41
    <eos>
    0.40
     working
    0.39
     rolling
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.