© 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. 5-CLT-HP
    7. 95010
    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
     journalistes
    -0.61
    OSSARY
    -0.59
     BoxDecoration
    -0.59
    RegressionTest
    -0.57
     avoient
    -0.55
     ancianos
    -0.54
     lèvres
    -0.54
     étanche
    -0.54
     periodistas
    -0.54
     mêmes
    -0.53
    POSITIVE LOGITS
     summer
    0.57
     fall
    0.54
     autumn
    0.52
     <=",
    0.51
     Valley
    0.49
    ########.
    0.49
    enity
    0.49
    insee
    0.48
     River
    0.47
     Merced
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.