© 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. 1-CLT-HP
    7. 46156
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.74
    tagHelperRunner
    -0.70
    <eos>
    -0.68
    ...
    -0.68
     disambiguazione
    -0.67
    rungsseite
    -0.66
    TagMode
    -0.66
    twimg
    -0.65
    mybatisplus
    -0.63
    '...
    -0.63
    POSITIVE LOGITS
     Jefus
    1.08
     Cæsar
    0.93
     pleaſure
    0.93
     Monfieur
    0.91
     purpoſe
    0.91
     Majefty
    0.89
     Shakspeare
    0.88
     Efq
    0.84
     himſelf
    0.81
    ſelf
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.